Generative Adversarial Networks (GANs) often exhibit unstable training dynamics and strong dependence on manually designed architectures, limiting scalability and robustness. This paper proposes HEAGAN, an efficient hybrid evolutionary neural architecture search framework for GANs. HEAGAN searches the generator architecture only, while the discriminator follows a fixed AutoGAN-style backbone throughout training and evaluation. HEAGAN couples a guided hybrid evolutionary search with a partial weight-sharing supernet to automate generator architecture discovery for unsupervised image synthesis. The search integrates genetic algorithms and particle swarm optimisation, while constrained weight sharing with dynamic node activation reduces weight coupling and mitigates multi-model forgetting during supernet optimisation. To improve training stability, an adaptive robust loss is incorporated, and a multi-objective formulation based on NSGA-II jointly optimises generation quality and distributional fidelity. Experiments on CIFAR-10, STL-10, CIFAR-100, and ImageNet32 show that HEAGAN consistently identifies competitive generator architectures with improved stability and strong transferability across datasets. On CIFAR-10, HEAGAN achieves an Inception Score of 8.99 ± 0.11 and a Fréchet Inception Distance of 8.20. Ablation studies further validate the individual contributions of the proposed components.

Fine-tuning large-scale Transformer-based models is computationally expensive due to the enormous parameter space. Low-Rank Adaptation (LoRA) substantially reduces the number of trainable parameters while maintaining performance; however, identifying the optimal LoRA configuration — such as rank r, scaling factor [Formula: see text], and insertion positions — remains challenging. To address this issue, we propose a zero-shot proxy metric, termed Gradient Projection Score (GPS), which enables rapid evaluation of candidate configurations using only a few forward and backward passes. Building upon this metric, we further introduce EvoLoRA, a zero-shot evolutionary architecture search method that jointly optimizes three objectives: performance proxy, evaluation stability, and trainable parameter size. EvoLoRA automatically discovers effective LoRA configurations across different models and datasets. Experimental results demonstrate that GPS is strongly correlated with final model performance; moreover, on tasks such as image classification and object detection, EvoLoRA markedly reduces search and training costs while generally outperforming other fine-tuning methods and manually designed LoRA configurations.

Diffusion models have achieved remarkable success in image generation, image super-resolution, and text-to-image synthesis. Despite their effectiveness, they face key challenges, notably long inference time and complex architectures that incur high computational costs. While various methods have been proposed to reduce inference steps and accelerate computation, the optimization of diffusion model architectures has received comparatively limited attention. To address this gap, we propose LDMOES (Lightweight Diffusion Models based on Multi-Objective Evolutionary Search), a framework that combines multi-objective evolutionary neural architecture search with knowledge distillation to design efficient UNet-based diffusion models. By adopting a modular search space, LDMOES effectively decouples architecture components for improved search efficiency. We validated our method on multiple datasets, including CIFAR-10, Tiny-ImageNet, CelebA-HQ [Formula: see text], and LSUN-church [Formula: see text]. Experiments show that LDMOES reduces multiply-accumulate operations (MACs) by approximately 40% in pixel space while outperforming the teacher model. When transferred to the larger-scale Tiny-ImageNet dataset, it still generates high-quality images with a competitive FID score of 4.16, demonstrating strong generalization ability. In latent space, MACs are reduced by about 50% with negligible performance loss. After transferring to the more complex LSUN-church dataset, the model surpasses baselines in generation quality while reducing computational cost by nearly 60%, validating the effectiveness and transferability of the multi-objective search strategy. Code and models will be available at https://github.com/GenerativeMind-arch/LDMOES .

Generative Adversarial Networks (GANs) have demonstrated remarkable success in high-quality image synthesis, with StyleGAN and its successor, StyleGAN2, achieving state-of-the-art performance in terms of realism and control over generated features. However, the large number of parameters and high floating-point operations per second (FLOPs) hinder real-time applications and scalability, posing challenges for deploying these models in resource-constrained environments such as edge devices and mobile platforms. To address this issue, we propose Evolutionary Channel Pruning for StyleGANs (ECP-StyleGANs), a novel algorithm that leverages evolutionary algorithms to compress StyleGAN and StyleGAN2 while maintaining competitive image quality. Our approach encodes pruning configurations as binary masks on the model's convolutional channels and iteratively refines them through selection, crossover, and mutation. By integrating carefully designed fitness functions that balance model complexity and generation quality, ECP-StyleGANs identifies optimally pruned architectures that reduce computational demands without compromising visual fidelity, achieving approximately a 4 × reduction in FLOPs and parameters, while maintaining visual fidelity with only a slight increase in FID (Fréchet Inception Distance) compared to the original un-pruned model. This study should be interpreted as a preliminary step towards the formulation and management of the generative AI pruning problem as a multi-objective optimisation task, aimed at enhancing the trade-off between model efficiency and image quality, thereby making large deep models more accessible for real-world applications such as edge devices and resource-constrained environments.

Designing effective neural architectures remains a central challenge in deep learning, and Neural Architecture Search (NAS) has become a popular tool for automating this process. However, many existing NAS approaches depend on hand-crafted architecture descriptors or shallow performance predictors, which fail to capture the structural complexity of candidate networks and often lead to unreliable search guidance. We introduce Graph Embedding Comparator with Isomorphic Multi-Comparison (GEC-IMC), an evolutionary NAS framework that learns architecture representations directly from their graph structure. A graph convolutional network encodes architectures into embeddings, while a contrastive learning strategy ensures that architectures with similar accuracy are mapped closer in the embedding space. On top of these embeddings, a comparator estimates the relative performance between two architectures, enabling more precise pairwise assessments during search. To further increase robustness, GEC-IMC incorporates an isomorphic multi-comparison mechanism, which evaluates multiple structurally equivalent variants of each architecture and aggregates their pairwise outcomes into a global score. This ranking score provides consistent feedback for evolutionary selection. Experiments on standard NAS benchmarks demonstrate that GEC-IMC achieves state-of-the-art performance with improved robustness over existing predictors. Ablation studies confirm the complementary roles of embedding learning and multi-comparison in enhancing search efficiency.

Software effort estimation predicts resources needed for a project, including person-hours and costs, and is vital for effective planning and budgeting. This paper compares two grammar-based evolutionary algorithms: grammar-based genetic programming (GGP) and grammatical evolution (GE). Both algorithms are tested on public project datasets and compared with machine learning models such as support vector machines, artificial neural networks, and least-squares linear regression. Results demonstrate that GGP and GE outperform alternative methods across two evaluation metrics, highlighting their effectiveness in estimating software effort.

Evolutionary neural architecture search (ENAS) automates the design of high-performing neural networks but is often hindered by the high computational cost of evaluating individual architectures. Surrogate models mitigate this issue by predicting performance, yet their accuracy depends on the quality of training data and their ability to utilise insights from real evaluations. This paper presents homogeneous encoding-based ENAS (HENAS), a novel method addressing these challenges through two key innovations: homogeneous architecture augmentation and confidence-based prediction. Through homogeneous architecture augmentation, HENAS exploits redundant encodings in the MobileNetV3 search space to generate multiple representations of the same architecture, enhancing the surrogate model’s training data without additional cost. Confidence-based prediction introduces a mechanism to identify architectures with uncertain performance estimates, prioritising them for evaluation. Integrated into an evolutionary framework, these techniques improve search efficiency and exploration. Experiments on CIFAR-10, CIFAR-100, and ImageNet show that HENAS achieves state-of-the-art performance with reduced computational expense. Ablation studies confirm the contributions of its core components, highlighting the value of redundancy exploitation and uncertainty management in surrogate-assisted ENAS.

Neural architecture search (NAS) has emerged as a promising technique for automating neural network design. However, many existing NAS methods rely on manually constructed architecture features, which often fail to capture the intricate structural relationships within network architectures. These limitations can mislead the performance predictors that depend on such features, hindering the search process. To address this challenge, we propose a novel architecture feature extraction framework that automatically learns and optimises feature representations. Specifically, we utilize graph convolutional networks (GCNs) to extract architecture features and employ contrastive learning to refine these features, producing graph embeddings that accurately represent the architecture. This embedding space ensures that architectures with similar performance are positioned closer together, while those with differing performance are spaced farther apart. Building on this representation, we develop an architecture embedding comparator that qualitatively predicts the performance relationship between two architectures. Our proposed method is referred to as Embedded Comparator for Evolutionary Naural Architecture Search (EmCENAS). Experimental results across several widely used NAS search spaces demonstrate the effectiveness of our proposed framework. Ablation studies further reveal the advantages and insights provided by our method, highlighting its potential to enhance NAS.

Modern neural architecture search (NAS) is inherently multi-objective balancing trade-offs such as accuracy, parameter count, and computational cost. This complexity makes NAS computationally expensive and nearly impossible to solve without efficient approximations. To address this, we propose a novel surrogate modelling approach that leverages an ensemble of Siamese network blocks to predict dominance relationships between candidate architectures. Lightweight and easy to train, the surrogate achieves 92% accuracy and replaces the crowding distance calculation in the survivor selection strategy with a heuristic rule based on model size. Integrated into a framework termed SiamNAS, this design eliminates costly evaluations during the search process. Experiments on NAS-Bench-201 demonstrate the framework's ability to identify Pareto-optimal solutions with significantly reduced computational costs. The proposed SiamNAS identified a final non-dominated set containing the best architecture in NAS-Bench-201 for CIFAR-10 and the second-best for ImageNet, in terms of test error rate, within 0.01 GPU days. This proof-of-concept study highlights the potential of the proposed Siamese network surrogate model to generalise to multi-tasking optimisation, enabling simultaneous optimisation across tasks. Additionally, it offers opportunities to extend the approach for generating Sets of Pareto Sets (SOS), providing diverse Pareto-optimal solutions for heterogeneous task settings.

Designing effective neural networks is a cornerstone of deep learning, and Neural Architecture Search (NAS) has emerged as a powerful tool for automating this process. Among the existing NAS approaches, Differentiable Architecture Search (DARTS) has gained prominence for its efficiency and ease of use, inspiring numerous advancements. Since the rise of Vision Transformers (ViT), researchers have applied NAS to explore ViT architectures, often focusing on macro-level search spaces and relying on discrete methods like evolutionary algorithms. While these methods ensure reliability, they face challenges in discovering innovative architectural designs, demand extensive computational resources, and are time-intensive. To address these limitations, we introduce Differentiable Architecture Search for Vision Transformer (DASViT), which bridges the gap in differentiable search for ViTs and uncovers novel designs. Experiments show that DASViT delivers architectures that break traditional Transformer encoder designs, outperform ViT-B/16 on multiple datasets, and achieve superior efficiency with fewer parameters and FLOPs.

In the context of neural system structure modeling and complex visual tasks, the effective integration of multi-scale features and contextual information is critical for enhancing model performance. This paper proposes a biologically inspired hybrid neural network architecture - CompEyeNet - which combines the global modeling capacity of transformers with the efficiency of lightweight convolutional structures. The backbone network, multi-attention transformer backbone network (MATBN), integrates multiple attention mechanisms to collaboratively model local details and long-range dependencies. The neck network, compound eye neck network (CENN), introduces high-resolution feature layers and efficient attention fusion modules to significantly enhance multi-scale information representation and reconstruction capability. CompEyeNet is evaluated on three authoritative medical image segmentation datasets: MICCAI-CVC-ClinicDB, ISIC2018, and MICCAI-tooth-segmentation, demonstrating its superior performance. Experimental results show that compared to models such as Deeplab, Unet, and the YOLO series, CompEyeNet achieves better performance with fewer parameters. Specifically, compared to the baseline model YOLOv11, CompEyeNet reduces the number of parameters by an average of 38.31%. On key performance metrics, the average Dice coefficient improves by 0.87%, the Jaccard index by 1.53%, Precision by 0.58%, and Recall by 1.11%. These findings verify the advantages of the proposed architecture in terms of parameter efficiency and accuracy, highlighting the broad application potential of bio-inspired attention-fusion hybrid neural networks in neural system modeling and image analysis.

Cloud cover experiences rapid fluctuations, significantly impacting the irradiance reaching the ground and causing frequent variations in photovoltaic power output. Accurate detection of thin and fragmented clouds is crucial for reliable photovoltaic power generation forecasting. In this paper, we introduce a novel cloud detection method, termed Adaptive Laplacian Coordination Enhanced Cross-Feature U-Net (ALCU-Net). This method augments the traditional U-Net architecture with three innovative components: an Adaptive Feature Coordination (AFC) module, an Adaptive Laplacian Cross-Feature U-Net with a Multi-Grained Laplacian-Enhanced (MLE) feature module, and a Criss-Cross Feature Fused Detection (CCFE) module. The AFC module enhances spatial coherence and bridges semantic gaps across multi-channel images. The Adaptive Laplacian Cross-Feature U-Net integrates features from adjacent hierarchical levels, using the MLE module to refine cloud characteristics and edge details over time. The CCFE module, embedded in the U-Net decoder, leverages criss-cross features to improve detection accuracy. Experimental evaluations show that ALCU-Net consistently outperforms existing cloud detection methods, demonstrating superior accuracy in identifying both thick and thin clouds and in mapping fragmented cloud patches across various environments, including oceans, polar regions, and complex ocean-land mixtures.

Generative Adversarial Networks (GANs) are effective for image generation, but their unstable training limits broader applications. Additionally, neural architecture search (NAS) for GANs with one-shot models often leads to insufficient subnet training, where subnets inherit weights from a supernet without proper optimization, further degrading performance. To address both issues, we propose Architecture Knowledge Distillation for Evolutionary GAN (AKD-EGAN). AKD-EGAN operates in two stages. First, architecture knowledge distillation (AKD) is used during supernet training to efficiently optimize subnetworks and accelerate learning. Second, a multi-objective evolutionary algorithm (MOEA) searches for optimal subnet architectures, ensuring efficiency by considering multiple performance metrics. This approach, combined with a strategy for architecture inheritance, enhances GAN stability and image quality. Experiments show that AKD-EGAN surpasses state-of-the-art methods, achieving a Fréchet Inception Distance (FID) of 7.91 and an Inception Score (IS) of 8.97 on CIFAR-10, along with competitive results on STL-10 (FID: 20.32, IS: 10.06). Code and models will be available at https://github.com/njit-ly/AKD-EGAN.

Neural Architecture Search (NAS) automates the design of deep neural networks but remains computationally expensive, particularly in multi-objective settings. Existing predictor-assisted evolutionary NAS methods suffer from slow convergence and rank disorder, which undermines prediction accuracy. To overcome these limitations, we propose CHENAS: a Classifier-assisted multi-objective Hybrid Evolutionary NAS framework. CHENAS combines the global exploration of evolutionary algorithms with the local refinement of gradient-based optimization to accelerate convergence and enhance solution quality. A novel dominance classifier predicts Pareto dominance relationships among candidate architectures, reframing multi-objective optimization as a classification task and mitigating rank disorder. To further improve efficiency, we employ a contrastive learning-based autoencoder that maps architectures into a continuous, structured latent space tailored for dominance prediction. Experiments on several benchmark datasets demonstrate that CHENAS outperforms state-of-the-art NAS approaches in identifying high-performing architectures across multiple objectives. Future work will focus on improving the computational efficiency of the framework and extending it to other application domains.

With global warming driving more extreme weather events, real-time monitoring and forecasting of severe convective weather are increasingly critical. This letter presents a multitask generative adversarial network (MT-GAN) to improve nowcasting (short-term prediction) of severe weather, specifically precipitation and lightning. MT-GAN forecasts with 6-min temporal resolution and up to 60-min lead times. Its dual-stream architecture handles radar reflectivity and lightning data, using an encoder-decoder framework with SimVP for temporal feature extraction. A two-level feature fusion enhances spatiotemporal predictions, while a Patch-D discriminator improves realism. Tested on a central China dataset, MT-GAN outperforms ConvLSTM and PredRNN++ in image quality and nowcasting accuracy, with a stronger emphasis on convective regions for better lightning initiation detection.

Biped robots have received increasing attention due to their human-like mechanical structure and good environmental adaptability. In this paper, a new Human-Simulated Intelligent Walking Control (HIWC) scheme is proposed to solve the stability problem of the most popular proportional differential (PD) control under model inaccuracy and disturbance, and further improve its control performance. Specifically, based on Human-Simulated Intelligent Control (HSIC), HIWC is a hierarchical control structure composed of a foot placement compensation (FPC) strategy at the high-level planning layer, and a multi-mode compensation controller (MCC) at the low-level (execution) layer. In FPC, a foot placement compensation algorithm is proposed to plan and correct the swing foots trajectory in real time. MCC consists of a PD and two adaptive compensation algorithms. MCC under bounded uncertainty is proven to be stable in this paper using the Lyapunov theorem. HIWC was tested and compared with PD and model predictive control (MPC) in three experiments on a physical robot platform for planar walking, push-pull, and uneven-ground walking. Experimental results show that the proposed HIWC is more flexible and accurate in controlling the robot’s movement.Note to Practitioners—This paper builds on the fact that PD controllers cannot be easily proven to be stable and do not provide accurate control for the biped robot walking problem. To address these issues, this paper proposes a novel control scheme namely Human-Simulated Intelligent Walking Control (HIWC) and belonging to the family of Human-Simulated Intelligent Control (HSIC) schemes. The proposed HIWC system has been compared against the model predictive control (MPC) and a proportional differential (PD) controller. The proposed HIWC, unlike PD controllers, is rigorously proven to be stable in the presence of model inaccuracy and disturbance. Furthermore, the experiments carried out on a real-world biped robot demonstrate the superiority of HIWC over PD and MPC in terms of control performance.

Neural architecture search (NAS) is a popular method that can automatically design deep neural network structures. However, designing a neural network using NAS is computationally expensive. This article proposes a gradient-guided evolutionary NAS (GENAS) to design convolutional neural networks (CNNs) for image classification. GENAS is a hybrid algorithm that combines evolutionary global and local search operators to evolve a population of subnets sampled from a supernet. Each candidate architecture is encoded as a table describing which operations are associated with the edges between nodes signifying feature maps. Besides, evolutionary optimization uses novel crossover and mutation operators to manipulate the subnets using the proposed tabular encoding. Every generations, the candidate architectures undergo a local search inspired by differentiable NAS. GENAS is designed to overcome the limitations of both evolutionary and gradient descent NAS. This algorithmic structure enables the performance assessment of the candidate architecture without retraining, thus limiting the NAS calculation time. Furthermore, subnet individuals are decoupled during evaluation to prevent strong coupling of operations in the supernet. The experimental results indicate that the searched structures achieve test errors of 2.45%, 16.86%, and 23.9% on CIFAR-10/100/ImageNet datasets and it costs only 0.26 GPU days on a graphic card. GENAS can effectively expedite the training and evaluation processes and obtain high-performance network structures.

Evolutionary neural architecture search (ENAS) is an approach to automating network architecture design. A primary challenge of ENAS is the demand for expensive computational resources, and many ENAS methods use surrogate models to reduce costs. However, existing architecture representation methods are not rich enough in capturing the information of architectures, making them inadequate for building effective surrogate models. Furthermore, existing research studies often rely on a single model or strategy to predict architecture performance, which is not always accurate or reliable. To alleviate these issues, this article proposes a dual-stage surrogate model based on graph neural networks (GNNs) for ENAS, namely dual-stage surrogate model for evolutionary neural architecture search (DSGENAS). First, to effectively represent the neural architectures for the surrogate model, we employ a GNN-based architecture embedding method to extract architecture features. Second, based on the architecture representation, a dual-stage surrogate model strategy is proposed and integrated into the ENAS framework. This strategy combines two surrogate models in the evolutionary search process, one for global performance-tier learning and the other for local performance relationship learning. Experimental results show that extracting architecture features through GNNs can achieve a more effective architecture representation. The two different surrogate models can jointly assist the search process in ENAS. Furthermore, DSGENAS can achieve accurate and stable prediction results, obtaining state-of-the-art results on neural architecture search (NAS) benchmarks.

The widespread use of machine learning (ML) in software engineering (SE) encounters a notable challenge: the need for various domain-specific parameters in algorithms. The issue arises when attempting to reuse these parameters across different applications, resulting in sub-optimal outcomes. This hindrance significantly contributes to the limited migration of ML solutions from research labs to industrial settings. This paper underscores the pressing need for novel research to tackle the overarching problem of generic algorithm customisation. To address this, we propose leveraging Automated Machine Learning (AutoML) approaches. These techniques automatically select intelligible models and their corresponding hyper-parameters for forecasting software defect-proneness. More specifically, this paper adapts an AutoML approach to the field of software defect prediction, namely a hyper-heuristic evolutionary algorithm for automatically designing decision tree algorithms (HEAD-DT), originally proposed to address a generic optimisation problem. We benchmark against the popular general software defect-proneness prediction framework (GSDP) and some standard classifiers. Experimental results reveal that the proposed HEAD-DT implementation surpasses other algorithms across three distinct evaluation measures.

Generative adversarial networks (GANs) are widely recognized for their impressive ability to generate realistic data. Despite the popularity of GANs, training them poses challenges such as mode collapse and instability. To address these issues, many variants enhance GAN performance through improvements in network architecture, modifications to loss functions, and the inclusion of regularization techniques. However, a limited number of methods focuses on optimising GAN performance from the optimiser's perspective, despite the distinct roles different optimisers play in training. Existing GANs typically employ a single optimiser throughout, with Adam being the default choice for GAN training. Approaches using multiple optimisers have shown improved performance but are often task-specific. This paper introduces a novel, portable approach that lever-ages the strengths of multiple training methods, with an evolutionary supervisor coordinating the training of different sections of the network. Initially, real-number-encoded vectors representing the optimiser for each sub-parameter layer undergo pro-gressive enhancement using a standard evolutionary algorithm (SGA). Through the evolutionary process, optimal optimiser combinations are retained based on the performance of the trained GAN. The proposed method, SGA-GANs, is validated on the CIFAR10 dataset by integrating the steps into five benchmark GAN models: GAN, DCGAN, BEGAN, WGAN, and WGAN-GP. Experimental results demonstrate that SGA-GANs outperforms single optimiser training methods, achieving superior evaluation results and generating higher-quality images. Source code can be found at https://github.com/lizzhang-spec/SGA-GANs.

Deep learning has gained significant popularity in recent years, particularly for tasks like image and speech recognition, natural language processing, and other intricate pattern recognition challenges. However, training a deep learning model involves tuning millions or even billions of parameters. Consequently, this training process becomes a large-scale optimisation problem associated with a mostly unknown but highly non-convex fitness landscape. In recent decades, advances in fitness landscape analysis have revolved around characterizing landscapes representing loss functions, with Local Optima Networks (LONs) emerging as a promising tool. This paper, while focusing on LeNet-5, leverages LON to address four key questions concerning the nature of the learning problem. We emphasize the impact of experimental conditions during the analysis phase on drawing conclusions about the problem's nature. The results shed light on parametrization and optimiser selection to enhance the analysis and comprehension of deep learning loss landscapes. In particular, we identify the presence and number of funnels in the landscape's structure, study the impact of the dataset on the nature of the problem, investigate how the choice of local search optimisers may influence conclusions about the problem's structure. Finally, sensitivity analysis was conducted on the perturbation strength of the Basin-Hopping sampling method for LON construction.

Neural architecture search (NAS) automates the design of neural networks, but faces high computational costs for evaluating the performance candidate architectures. Surrogate-assisted NAS methods use approximate computational models to get predictive estimation instead of real complete training, but also face the challenge of maintaining the balance between training cost and predictive effectiveness. In this paper, we propose a progressive neural predictor that uses score-based sampling (PNSS) to improve the performance of the surrogate model with limited training data. Different from existing algorithms that rely on initial sample selection, PNSS uses an online method to progressively select new samples of the surrogate model based on potential information from the previous search process. During the iterative process, the sampled scores are dynamically adjusted based on the prediction rankings in each round to keep track of good architectures, which gradually optimises the surrogate model. In this way, the processes of training the predictor and searching for architectures are jointly combined to improve the efficiency of sample utilization. In addition, the surrogate model with different degrees of training is assigned prediction confidence equal to the accuracy of the current stage. Experiments are conducted on NAS-Bench-101 and NAS-Bench-201 benchmarks. The experimental results show that the proposed PNSS algorithm outperforms the existing methods with limited training samples. In addition, visualisation of the search process and ablation study also shows the effectiveness of the progressive search.

In many modern machine learning (ML) models, attention mechanisms (AMs) play a crucial role in processing data and identifying significant parts of the inputs, whether these are text or images. This selective focus enables subsequent stages of the model to achieve improved classification performance. Traditionally, AMs are applied as a preprocessing substructure before a neural network, such as in encoder/decoder architectures. In this paper, we extend the application of AMs to intermediate stages of data propagation within ML models. Specifically, we propose a generalized attention mechanism (GAM), which can be integrated before each layer of a neural network for classification tasks. The proposed GAM allows for at each layer/step of the ML architecture identification of the most relevant sections of the intermediate results. Our experimental results demonstrate that incorporating the proposed GAM into various ML models consistently enhances the accuracy of these models. This improvement is achieved with only a marginal increase in the number of parameters, which does not significantly affect the training time.

The optimization of robot controller parameters is a crucial task for enhancing robot performance, yet it often presents challenges due to the complexity of multi-objective, multi-dimensional multi-parameter optimization. This paper introduces a novel approach aimed at efficiently optimizing robot controller parameters to enhance its motion performance. While spiking neural P systems have shown great potential in addressing optimization problems, there has been limited research and validation concerning their application in continuous numerical, multi-objective, and multi-dimensional multi-parameter contexts. To address this research gap, our paper proposes the Entropy-Weighted Numerical Gradient Optimization Spiking Neural P System, which combines the strengths of entropy weighting and spiking neural P systems. First, the introduction of entropy weighting eliminates the subjectivity of weight selection, enhancing the objectivity and reproducibility of the optimization process. Second, our approach employs parallel gradient descent to achieve efficient multi-dimensional multi-parameter optimization searches. In conclusion, validation results on a biped robot simulation model show that our method markedly enhances walking performance compared to traditional approaches and other optimization algorithms. We achieved a velocity mean absolute error at least 35% lower than other methods, with a displacement error two orders of magnitude smaller. This research provides an effective new avenue for performance optimization in the field of robotics.

Machine learning algorithms are commonly used for quickly and efficiently counting people from a crowd. Test-time adaptation methods for crowd counting adjust model parameters and employ additional data augmentation to better adapt the model to the specific conditions encountered during testing. The majority of current studies concentrate on unsupervised domain adaptation. These approaches commonly perform hundreds of epochs of training iterations, requiring a sizable number of unannotated data of every new target domain apart from annotated data of the source domain. Unlike these methods, we propose a meta-test-time adaptive crowd counting approach called CrowdTTA, which integrates the concept of test-time adaptation into the meta-learning framework and makes it easier for the counting model to adapt to the unknown test distributions. To facilitate the reliable supervision signal at the pixel level, we introduce uncertainty by inserting the dropout layer into the counting model. The uncertainty is then used to generate valuable pseudo labels, serving as effective supervisory signals for adapting the model. In the context of meta-learning, one image can be regarded as one task for crowd counting. In each iteration, our approach is a dual-level optimization process. In the inner update, we employ a self-supervised consistency loss function to optimize the model so as to simulate the parameters update process that occurs during the test phase. In the outer update, we authentically update the parameters based on the image with ground truth, improving the model's performance and making the pseudo labels more accurate in the next iteration. At test time, the input image is used for adapting the model before testing the image. In comparison to various supervised learning and domain adaptation methods, our results via extensive experiments on diverse datasets showcase the general adaptive capability of our approach across datasets with varying crowd densities and scales.

Spiking neural membrane systems (SN P systems) are a class of bio-inspired models inspired by the activities and connectivity of neurons. Extensive studies have been made on SN P systems with synchronization-based communication, while further efforts are needed for the systems with rhythm-based communication. In this work, we design an asynchronous SN P system with resonant connections where all the enabled neurons in the same group connected by resonant connections should instantly produce spikes with the same rhythm. In the designed system, each of the three modules implements one type of the three operations associated with the edge detection of digital images, and they collaborate each other through the resonant connections. An algorithm called EDSNP for edge detection is proposed to simulate the working of the designed asynchronous SN P system. A quantitative analysis of EDSNP and the related methods for edge detection had been conducted to evaluate the performance of EDSNP. The performance of the EDSNP in processing the testing images is superior to the compared methods, based on the quantitative metrics of accuracy, error rate, mean square error, peak signal-to-noise ratio and true positive rate. The results indicate the potential of the temporal firing and the proper neuronal connections in the SN P system to achieve good performance in edge detection.

Feature selection (FS) is recognized for its role in enhancing the performance of learning algorithms, especially for high-dimensional datasets. In recent times, FS has been framed as a multi-objective optimization problem, leading to the application of various multi-objective evolutionary algorithms (MOEAs) to address it. However, the solution space expands exponentially with the dataset’s dimensionality. Simultaneously, the extensive search space often results in numerous local optimal solutions due to a large proportion of unrelated and redundant features [H. Adeli and H. S. Park, Fully automated design of super-high-rise building structures by a hybrid ai model on a massively parallel machine, AI Mag. 17 (1996) 87–93]. Consequently, existing MOEAs struggle with local optima stagnation, particularly in large-scale multi-objective FS problems (LSMOFSPs). Different LSMOFSPs generally exhibit unique characteristics, yet most existing MOEAs rely on a single candidate solution generation strategy (CSGS), which may be less efficient for diverse LSMOFSPs [H. S. Park and H. Adeli, Distributed neural dynamics algorithms for optimization of large steel structures, J. Struct. Eng. ASCE 123 (1997) 880–888; M. Aldwaik and H. Adeli, Advances in optimization of highrise building structures, Struct. Multidiscip. Optim. 50 (2014) 899–919; E. G. González, J. R. Villar, Q. Tan, J. Sedano and C. Chira, An efficient multi-robot path planning solution using a* and coevolutionary algorithms, Integr. Comput. Aided Eng. 30 (2022) 41–52]. Moreover, selecting an appropriate MOEA and determining its corresponding parameter values for a specified LSMOFSP is time-consuming. To address these challenges, a multi-objective self-adaptive particle swarm optimization (MOSaPSO) algorithm is proposed, combined with a rapid nondominated sorting approach. MOSaPSO employs a self-adaptive mechanism, along with five modified efficient CSGSs, to generate new solutions. Experiments were conducted on ten datasets, and the results demonstrate that the number of features is effectively reduced by MOSaPSO while lowering the classification error rate. Furthermore, superior performance is observed in comparison to its counterparts on both the training and test sets, with advantages becoming increasingly evident as the dimensionality increases.

Generative adversarial networks (GANs) are a powerful generative technique but frequently face challenges with training stability. Network architecture plays a significant role in determining the final output of GANs, but designing a fine architecture demands extensive domain expertise. This paper aims to address this issue by searching for high-performance generator’s architectures through neural architecture search (NAS). The proposed approach, called evolutionary weight sharing generative adversarial networks (EWSGAN), is based on weight sharing and comprises two steps. First, a supernet of the generator is trained using weight sharing. Second, a multi-objective evolutionary algorithm (MOEA) is employed to identify optimal subnets from the supernet. These subnets inherit weights directly from the supernet for fitness assessment. Two strategies are used to stabilise the training of the generator supernet: a fair single-path sampling strategy and a discarding strategy. Experimental results indicate that the architecture searched by our method achieved a new state-of-the-art among NAS-GAN methods with a Fréchet inception distance (FID) of 9.09 and an inception score (IS) of 8.99 on the CIFAR-10 dataset. It also demonstrates competitive performance on the STL-10 dataset, achieving FID of 21.89 and IS of 10.51.

Existing unsupervised domain adaptation (UDA) methods rely on aligning the features from the source and target domains explicitly or implicitly in a common space (i.e., the domain invariant space). Explicit distribution matching ignores the discriminability of learned features, while the implicit counterpart such as self-supervised learning suffers from pseudo-label noises. With distribution alignment, it is challenging to acquire a common space which maintains fully the discriminative structure of both domains. In this work, we propose a novel HomeomorphisM Alignment (HMA) approach characterized by aligning the source and target data in two separate spaces. Specifically, an invertible neural network based homeomorphism is constructed. Distribution matching is then used as a sewing up tool for connecting this homeomorphism mapping between the source and target feature spaces. Theoretically, we show that this mapping can preserve the data topological structure (e.g., the cluster/group structure). This property allows for more discriminative model adaptation by leveraging both the original and transformed features of source data in a supervised manner, and those of target domain in an unsupervised manner (e.g., prediction consistency). Extensive experiments demonstrate that our method can achieve the state-of-the-art results. Code is released at https://github.com/buerzlh/HMA.

Existing Unsupervised Domain Adaptation (UDA) methods typically attempt to perform knowledge transfer in a domain-invariant space explicitly or implicitly. In practice, however, the obtained features is often mixed with domain-specific information which causes performance degradation. To overcome this fundamental limitation, this article presents a novel independent feature decomposition and instance alignment method (IndUDA in short). Specifically, based on an invertible flow, we project the base features into a decomposed latent space with domain-invariant and domain-specific dimensions. To drive semantic decomposition independently, we then swap the domain-invariant part across source and target domain samples with the same category and require their inverted features are consistent in class-level with the original features. By treating domain-specific information as noise, we replace it by Gaussian noise and further regularize source model training by instance alignment, i.e., requiring the base features close to the corresponding reconstructed features, respectively. Extensive experiment results demonstrate that our method achieves state-of-the-art performance on popular UDA benchmarks. The appendix and code are available at https://github.com/ayombeach/IndUDA.

Dropout is an effective method of mitigating over-fitting while training deep neural networks (DNNs). This method consists of switching off (dropping) some of the neurons of the DNN and training it by keeping the remaining neurons active. This approach makes the DNN general and resilient to changes in its inputs. However, the probability of a neuron belonging to a layer to be dropped, the ’dropout rate’, is a hard-to-tune parameter that affects the performance of the trained model. Moreover, there is no reason, besides being more practical during parameter tuning, why the dropout rate should be the same for all neurons across a layer. This paper proposes a novel method to guide the dropout rate based on an evolutionary algorithm . In contrast to previous studies, we associate a dropout with each individual neuron of the network, thus allowing more flexibility in the training phase. The vector encoding the dropouts for the entire network is interpreted as the candidate solution of a bi-objective optimisation problem, where the first objective is the error reduction due to a set of dropout rates for a given data batch, while the second objective is the distance of the used dropout rates from a pre-arranged constant. The second objective is used to control the dropout rates and prevent them from becoming too small, hence ineffective; or too large, thereby dropping a too-large portion of the network. Experimental results show that the proposed method, namely GADropout, produces DNNs that consistently outperform DNNs designed by other dropout methods, some of them being modern advanced dropout methods representing the state-of-the-art. GADroput has been tested on multiple datasets and network architectures.

A Generative Adversarial Network (GAN) can learn the relationship between two image domains and achieve unpaired image-to-image translation. One of the breakthroughs was Cycle-consistent Generative Adversarial Networks (CycleGAN), which is a popular method to transfer the content representations from the source domain to the target domain. Existing studies have gradually improved the performance of CycleGAN models by modifying the network structure or loss function of CycleGAN. However, these methods tend to suffer from training instability and the generators lack the ability to acquire the most discriminating features between the source and target domains, thus making the generated images of low fidelity and few texture details. To overcome these issues, this paper proposes a new method that combines Evolutionary Algorithms (EAs) and Attention Mechanisms to train GANs. Specifically, from an initial CycleGAN, binary vectors indicating the activation of the weights of the generators are progressively improved upon by means of an EA. At the end of this process, the best-performing configurations of generators can be retained for image generation. In addition, to address the issues of low fidelity and lack of texture details on generated images, we make use of the channel attention mechanism. The latter component allows the candidate generators to learn important features of real images and thus generate images with higher quality. The experiments demonstrate qualitatively and quantitatively that the proposed method, namely, Attention evolutionary GAN (AevoGAN) alleviates the training instability problems of CycleGAN training. In the test results, the proposed method can generate higher quality images and obtain better results than the CycleGAN training methods present in the literature, in terms of Inception Score (IS), Fréchet Inception Distance (FID) and Kernel Inception Distance (KID).

An important problem in data science, feature selection (FS) consists of finding the optimal subset of features and eliminating irrelevant or redundant features. The FS task on high-dimensional data is challenging for the FS methods currently available in the literature. To overcome this limitation, we propose a novel feature selection method called External Attention-Based Feature Ranker for Large-Scale Feature Selection (EAR-FS) whose function is based on the logic of an attention mechanism and a hybrid metaheuristic. EAR-FS comprises three interdependent modules: (1) in the training module design, a multilayer perceptron network endowed with an attention module is trained to fit the dataset; (2) in feature ranking by attention, the trained attention module is used for attention updating and to rank features according to their importance; 3) in subset generation, a two-stage heuristic approach is applied to determine a small number of features that still guarantee high-accuracy performance. The experimental benchmark comprised 26 datasets of small, large and very large sizes, ranging from 15 to 12,533 features. Experiments performed against the state-of-the-art algorithms of FS show that our algorithm is efficient at selecting a small number of features from large datasets while guaranteeing excellent levels of classification accuracy. For instance, EAR-FS demonstrated its capability to reduce the features of the 11 Tumor dataset by 97% while maintaining a classifier accuracy of over 93%.

This paper presents an experimental study on memetic strategies to enhance the performance of population-based metaheuristics for multimodal optimisation. The purpose of this work is to devise some recommendations about algorithmic design to allow a successful combination of local search and niching techniques. Six memetic strategies are presented and tested over five population-based algorithms endowed with niching techniques. Experimental results clearly show that local search enhances the performance of the framework for multimodal optimisation in terms of both peak ratio and success rate. The most promising results are obtained by the variants that employ an archive that pre-selects the solutions undergoing local search thus avoiding computational waste. Furthermore, promising results are obtained by variants that reduce the exploitation pressure of the population-based framework by using a simulated annealing logic in the selection process, leaving the exploitation task to the local search.

Spiking neural P systems (abbreviated as SNP systems) are models of computation that mimic the behavior of biological neurons. The spiking neural P systems with communication on request (abbreviated as SNQP systems) are a recently developed class of SNP system, where a neuron actively requests spikes from the neighboring neurons instead of passively receiving spikes. It is already known that small SNQP systems, with four unbounded neurons, can achieve Turing universality. In this context, 'unbounded' means that the number of spikes in a neuron is not capped. This work investigates the dependency of the number of unbounded neurons on the computation capability of SNQP systems. Specifically, we prove that (1) SNQP systems composed entirely of bounded neurons can characterize the family of finite sets of numbers; (2) SNQP systems containing two unbounded neurons are capable of generating the family of semilinear sets of numbers; (3) SNQP systems containing three unbounded neurons are capable of generating nonsemilinear sets of numbers. Moreover, it is obtained in a constructive way that SNQP systems with two unbounded neurons compute the operations of Boolean logic gates, i.e., OR, AND, NOT, and XOR gates. These theoretical findings demonstrate that the number of unbounded neurons is a key parameter that influences the computation capability of SNQP systems.

Spiking neural P systems (SN P systems), inspired by biological neurons, are introduced as symbolical neural-like computing models that encode information with multisets of symbolized spikes in neurons and process information by using spike-based rewriting rules. Inspired by neuronal activities affected by enzymes, a numerical variant of SN P systems called enzymatic numerical spiking neural P systems (ENSNP systems) is proposed wherein each neuron has a set of variables with real values and a set of enzymatic activation-production spiking rules, and each synapse has an assigned weight. By using spiking rules, ENSNP systems can directly implement mathematical methods based on real numbers and continuous functions. Furthermore, ENSNP systems are used to model ENSNP membrane controllers (ENSNP-MCs) for robots implementing wall following. The trajectories, distances from the wall, and wheel speeds of robots with ENSNP-MCs for wall following are compared with those of a robot with a membrane controller for wall following. The average error values of the designed ENSNP-MCs are compared with three recently fuzzy logical controllers with optimization algorithms for wall following. The experimental results showed that the designed ENSNP-MCs can be candidates as efficient controllers to control robots implementing the task of wall following.

Biological brains have a natural capacity for resolving certain classification tasks. Studies on biologically plausible spiking neurons, architectures and mechanisms of artificial neural systems that closely match biological observations while giving high classification performance are gaining momentum. Spiking neural P systems (SN P systems) are a class of membrane computing models and third-generation neural networks that are based on the behavior of biological neural cells and have been used in various engineering applications. Furthermore, SN P systems are characterized by a highly flexible structure that enables the design of a machine learning algorithm by mimicking the structure and behavior of biological cells without the over-simplification present in neural networks. Based on this aspect, this paper proposes a novel type of SN P system, namely, layered SN P system (LSN P system), to solve classification problems by supervised learning. The proposed LSN P system consists of a multi-layer network containing multiple weighted fuzzy SN P systems with adaptive weight adjustment rules. The proposed system employs specific ascending dimension techniques and a selection method of output neurons for classification problems. The experimental results obtained using benchmark datasets from the UCI machine learning repository and MNIST dataset demonstrated the feasibility and effectiveness of the proposed LSN P system. More importantly, the proposed LSN P system presents the first SN P system that demonstrates sufficient performance for use in addressing real-world classification problems.

Effective implementations of Memetic Algorithms often integrate, within their design, problem-based pieces of information. When no information is known, an efficient MA can still be designed after a preliminary analysis of the problem. This approach is usually referred to as Fitness Landscape Analysis (FLA). This paper proposes a FLA technique to analyse the epistasis of continuous optimisation problems and estimate those directions, within a multi-dimensional space, associated with maximum and minimum directional derivatives. This estimation is achieved by making use of the covariance matrix associated with a distribution of points whose objective function value is below (in case of minimisation) a threshold. The eigenvectors and eigenvalues of the covariance matrix provide important pieces of information about the geometry of the problem and are then used to design a memetic operator that is a local search belonging to the family of generalised Pattern Search. A restarting mechanism enables a progressive characterisation of the fitness landscape. Numerical results show that the proposed approach successfully explore ill-conditioned basins of attractions and outperforms the standard pattern search as well as a pattern search recently proposed in the literature and partially based on a similar design logic. The proposed local search based on FLA also displays a performance competitive with that of other types of local search.

In video-based point cloud compression (V-PCC), one geometry video and one color video are generated from a dynamic point cloud. Then, the two videos are compressed independently using a state-of-the-art video coder. In the Moving Picture Experts Group (MPEG) V-PCC test model, the quantization parameters for a given group of frames are constrained according to a fixed offset rule. For example, for the low-delay configuration, the difference between the quantization parameters of the first frame and the quantization parameters of the following frames in the same group is zero by default. We show that the rate-distortion performance of the V-PCC test model can be improved by lifting this constraint and considering the ratedistortion optimization problem as a multi-variable constrained combinatorial optimization problem where the variables are the quantization parameters of all frames. To solve the optimization problem, we use a variant of the differential evolution algorithm. Experimental results for the low-delay configuration show that our method can achieve a Bjøntegaard delta bitrate of up to -43.04% and more accurate rate control (average bitrate error to the target bitrate of 0.45% vs. 10.75%) compared to the state-of- the-art method, which optimizes the rate-distortion performance subject to the test model default offset rule. We also show that our optimization strategy can be used to improve the rate-distortion performance of two-dimensional video coders.

With the development of deep learning, the design of an appropriate network structure becomes fundamental. In recent years, the successful practice of Neural Architecture Search (NAS) has indicated that an automated design of the network structure can efficiently replace the design performed by human experts. Most NAS algorithms make the assumption that the overall structure of the network is linear and focus solely on accuracy to assess the performance of candidate networks. This paper introduces a novel NAS algorithm based on a multi-objective modeling of the network design problem to design accurate Convolutional Neural Networks (CNNs) with a small structure. The proposed algorithm makes use of a graph-based representation of the solutions which enables a high flexibility in the automatic design. Furthermore, the proposed algorithm includes novel ad-hoc crossover and mutation operators. We also propose a mechanism to accelerate the evaluation of the candidate solutions. Experimental results demonstrate that the proposed NAS approach can design accurate neural networks with limited size.

Echo state networks (ESNs), belonging to the family of recurrent neural networks (RNNs), are suitable for addressing complex nonlinear tasks due to their rich dynamic characteristics and easy implementation. The reservoir of the ESN is composed of a large number of sparsely connected neurons with randomly generated weight matrices. How to set the structural parameters of the ESN becomes a difficult problem in practical applications. Traditionally, the design of the parameters of the ESN structure is performed manually. The manual adjustment of the ESN parameters is not convenient since it is an extremely challenging and time-consuming task. This paper proposes an ensemble of five particle swarm optimization (PSO) strategies to design the structure of ESN and then reduce the manual intervention in the design process. An adaptive selection mechanism is used for each particle in the evolution to select a strategy from the strategy candidate pool for evolution. In addition, leaky integration neurons are used as reservoir internal neurons, which are added within the adaptive mechanism for optimization. The root mean squared error (RMSE) is adopted as the evaluation criterion. The experimental results on Mackey-Glass time series benchmark dataset show that the proposed method outperforms other traditional evolutionary methods. Furthermore, experimental results on electrocardiogram dataset show that the proposed method on the ensemble of PSO displays an excellent performance on real-world problems.

Several variants of spiking neural P systems (SNPS) have been presented in the literature to perform arithmetic operations. However, each of these variants was designed only for one specific arithmetic operation. In this paper, a complete arithmetic calculator implemented by SNPS is proposed. An application of the proposed calculator to information fusion is also proposed. The information fusion is implemented by integrating the following three elements: (1) an addition and subtraction SNPS already reported in the literature; (2) a modified multiplication and division SNPS; (3) a novel storage SNPS, i.e. a method based on SNPS is introduced to calculate basic probability assignment of an event. This is the first attempt to apply arithmetic operation SNPS to fuse multiple information. The effectiveness of the presented general arithmetic SNPS calculator is verified by means of several examples.

Optimization Spiking Neural P System (OSNPS) is the first membrane computing model to directly derive an approximate solution of combinatorial problems with a specific reference to the 0/1 knapsack problem. OSNPS is composed of a family of parallel Spiking Neural P Systems (SNPS) that generate candidate solutions of the binary combinatorial problem and a Guider algorithm that adjusts the spiking probabilities of the neurons of the P systems. Although OSNPS is a pioneering structure in membrane computing optimization, its performance is competitive with that of modern and sophisticated metaheuristics for the knapsack problem only in low dimensional cases. In order to overcome the limitations of OSNPS, this paper proposes a novel Dynamic Guider algorithm which employs an adaptive learning and a diversity-based adaptation to control its moving operators. The resulting novel membrane computing model for optimization is here named Adaptive Optimization Spiking Neural P System (AOSNPS). Numerical result shows that the proposed approach is effective to solve the 0/1 knapsack problems and outperforms multiple various algorithms proposed in the literature to solve the same class of problems even for a large number of items (high dimensionality). Furthermore, case studies show that a AOSNPS is effective in fault sections estimation of power systems in different types of fault cases: including a single fault, multiple faults and multiple faults with incomplete and uncertain information in the IEEE 39 bus system and IEEE 118 bus system.

Memetic Algorithms are traditionally composed of an evolutionary framework and one or more local search elements. However, modern generation Memetic Algorithms do not necessarily follow a pre-established scheme and are hybrid structures of various types. By following these modern trends, the present paper proposes an original and unconventional adaptive memetic structure generated by the hybridisation of a set of theoretical computational models, namely P Systems, and an evolutionary algorithm employing adaptation rules and moving operators inspired by Evolution Strategies. The resulting memetic algorithm, namely Adaptive Optimisation Spiking Neural P System (AOSNPS), is a tailored algorithm to solve optimisation problems with binary encoding. More specifically AOSNPS is composed of a family of parallel spiking neural P systems, each of them generating a binary vector representing a candidate solution on the basis of internal probability parameters and an adaptive Evolutionary Guider Algorithm that evolves the probabilities encoded in each P system. Numerical result shows that the proposed approach is effective to solve the 0/1 knapsack problem and outperforms various algorithms proposed in the literature to solve the same class of problems.

The design of each agent composing a Memetic Algorithm (MA) is a delicate task which often requires prior knowledge of the problem to be effective. This paper proposes a method to analyse one feature of the fitness landscape, that is the epistasis, with the aim of designing efficient local search algorithms for Memetic Frameworks. The proposed Analysis of Epistasis performs a sampling of points within the basin of attraction and builds a data set containing those candidate solutions whose objective function value falls below a threshold. The covariance matrix associated with this data set is then calculated. The eigenvectors of this covariance matrix are then computed and used as the reference system for the local search: a change of variables is performed and then the local search is performed on the new variables. The Analysis of Epistasis has been implemented on the three local search algorithms composing a popular MA called Multiple Trajectory Search (MTS). Numerical results show that the three modified local search algorithms outperform their original counterparts.

Spiking neural P systems are a class of third generation neural networks belonging to the framework of membrane computing. Spiking neural P systems with communication on request (SNQ P systems) are a type of spiking neural P system where the spikes are requested from neighboring neurons. SNQ P systems have previously been proved to be universal (computationally equivalent to Turing machines) when two types of spikes are considered. This paper studies a simplified version of SNQ P systems, i.e. SNQ P systems with one type of spike. It is proved that one type of spike is enough to guarantee the Turing universality of SNQ P systems. Theoretical results are shown in the cases of the SNQ P system used in both generating and accepting modes. Furthermore, the influence of the number of unbounded neurons (the number of spikes in a neuron is not bounded) on the computation power of SNQ P systems with one type of spike is investigated. It is found that SNQ P systems functioning as number generating devices with one type of spike and four unbounded neurons are Turing universal.

Spiking Neural [Formula: see text] Systems are Neural System models characterized by the fact that each neuron mimics a biological cell and the communication between neurons is based on spikes. In the Spiking Neural [Formula: see text] systems investigated so far, the application of evolution rules depends on the contents of a neuron (checked by means of a regular expression). In these [Formula: see text] systems, a specified number of spikes are consumed and a specified number of spikes are produced, and then sent to each of the neurons linked by a synapse to the evolving neuron. [Formula: see text]In the present work, a novel communication strategy among neurons of Spiking Neural [Formula: see text] Systems is proposed. In the resulting models, called Spiking Neural [Formula: see text] Systems with Communication on Request, the spikes are requested from neighboring neurons, depending on the contents of the neuron (still checked by means of a regular expression). Unlike the traditional Spiking Neural [Formula: see text] systems, no spikes are consumed or created: the spikes are only moved along synapses and replicated (when two or more neurons request the contents of the same neuron). [Formula: see text]The Spiking Neural [Formula: see text] Systems with Communication on Request are proved to be computationally universal, that is, equivalent with Turing machines as long as two types of spikes are used. Following this work, further research questions are listed to be open problems.

This paper presents a neural system-based technique for segmenting short impaired speech utterances into silent, unvoiced, and voiced sections. Moreover, the proposed technique identifies those points of the (voiced) speech where the spectrum becomes steady. The resulting technique thus aims at detecting that limited section of the speech which contains the information about the potential impairment of the speech. This section is of interest to the speech therapist as it corresponds to the possibly incorrect movements of speech organs (lower lip and tongue with respect to the vocal tract). Two segmentation models to detect and identify the various sections of the disordered (impaired) speech signals have been developed and compared. The first makes use of a combination of four artificial neural networks. The second is based on a support vector machine (SVM). The SVM has been trained by means of an ad hoc nested algorithm whose outer layer is a metaheuristic while the inner layer is a convex optimization algorithm. Several metaheuristics have been tested and compared leading to the conclusion that some variants of the compact differential evolution (CDE) algorithm appears to be well-suited to address this problem. Numerical results show that the SVM model with a radial basis function is capable of effective detection of the portion of speech that is of interest to a therapist. The best performance has been achieved when the system is trained by the nested algorithm whose outer layer is hybrid-population-based/CDE. A population-based approach displays the best performance for the isolation of silence/noise sections, and the detection of unvoiced sections. On the other hand, a compact approach appears to be clearly well-suited to detect the beginning of the steady state of the voiced signal. Both the proposed segmentation models display outperformed two modern segmentation techniques based on Gaussian mixture model and deep learning.

This paper proposes a novel adaptive local search algorithm for tackling real-valued (or continuous) dynamic optimization problems. The proposed algorithm is a simple single-solution based metaheuristic that perturbs the variables separately to select the search direction for the following step and adapts its step size to the gradient. The search directions that appear to be the most promising are rewarded by a step size increase while the unsuccessful moves attempt to reverse the search direction with a reduced step size. When the environment is subject to changes, a new solution is sampled and crosses over the best solution in the previous environment. Furthermore, the algorithm makes use of a small archive where the best solutions are saved. Experimental results show that the proposed algorithm, despite its simplicity, is competitive with complex population-based algorithms for tested dynamic optimization problems.

The present study is conducted in two phases. In the first phase we analyze the different aspects of gray image watermarking in a colored host. Robustness and imperceptibility are used as analysis parameters. The approaches explored and compared in this study are - watermark embedding with any one of the three RGB (Red-Green-Blue) components (single channel embedding), multichannel watermark embedding (same watermark with all channels) and multichannel embedding with equally segmented watermark. SVD (Singular Value Decomposition) is used to calculate the singular values of host image and then appropriate scaling factor isused to embed the watermark and the watermarked image is subjected to different attacks. To secure the watermark from an unauthorized access Arnold transform is implemented. From the simulation results it is observed that segmented watermark approach is better than the other two approaches in terms of both robustness and imperceptibility. In the second phase, change of robustness and imperceptibility is studied with the change of scaling factor for which PSO (Particle swarm optimization) is employed to determine the optimal values of scaling factor. The results here indicate that the use of different scaling factors (optimal) for each RGB component provides better result in comparison to a single (optimal) scaling factor in segmented multichannel approach. Overall, the experimental analysis shows that the equal distribution of gray watermark over RGB components with PSO optimized scaling factors provides significant improvement in the quality of watermarked image and the quality of retrieved watermark even from the distorted watermarked image.

The present study, proposes an optimization algorithm for solving the continuous global optimization problems. The basic framework selected for modeling the algorithm is Artificial Bee Colony (ABC). The proposed variant is called ABC with changing factor or CF-ABC. The proposed CF-ABC tries to maintain a tradeoff between exploration and exploitation so as to obtain reasonably good results. The proposed algorithm is implemented on the six benchmark functions and four engineering design problems. Simulated results illustrate the efficiency of the CF-ABC in terms of convergence speed and mean value.

We propose Multi-Strategy Coevolving Aging Particles (MS-CAP), a novel population-based algorithm for black-box optimization. In a memetic fashion, MS-CAP combines two components with complementary algorithm logics. In the first stage, each particle is perturbed independently along each dimension with a progressively shrinking (decaying) radius, and attracted towards the current best solution with an increasing force. In the second phase, the particles are mutated and recombined according to a multi-strategy approach in the fashion of the ensemble of mutation strategies in Differential Evolution. The proposed algorithm is tested, at different dimensionalities, on two complete black-box optimization benchmarks proposed at the Congress on Evolutionary Computation 2010 and 2013. To demonstrate the applicability of the approach, we also test MS-CAP to train a Feedforward Neural Network modeling the kinematics of an 8-link robot manipulator. The numerical results show that MS-CAP, for the setting considered in this study, tends to outperform the state-of-the-art optimization algorithms on a large set of problems, thus resulting in a robust and versatile optimizer.

Membrane systems (also called P systems) refer to the computing models abstracted from the structure and the functioning of the living cell as well as from the cooperation of cells in tissues, organs, and other populations of cells. Spiking neural P systems (SNPS) are a class of distributed and parallel computing models that incorporate the idea of spiking neurons into P systems. To attain the solution of optimization problems, P systems are used to properly organize evolutionary operators of heuristic approaches, which are named as membrane-inspired evolutionary algorithms (MIEAs). This paper proposes a novel way to design a P system for directly obtaining the approximate solutions of combinatorial optimization problems without the aid of evolutionary operators like in the case of MIEAs. To this aim, an extended spiking neural P system (ESNPS) has been proposed by introducing the probabilistic selection of evolution rules and multi-neurons output and a family of ESNPS, called optimization spiking neural P system (OSNPS), are further designed through introducing a guider to adaptively adjust rule probabilities to approximately solve combinatorial optimization problems. Extensive experiments on knapsack problems have been reported to experimentally prove the viability and effectiveness of the proposed neural system.

The super-fit scheme, consisting of injecting an individual with high fitness into the initial population of an algorithm, has shown to be a simple and effective way to enhance the algorithmic performance of the population-based algorithm. Whether the super-fit individual is based on some prior knowledge on the optimization problem or is derived from an initial step of pre-processing, e.g. a local search, this mechanism has been applied successfully in various examples of evolutionary and swarm intelligence algorithms. This paper presents an unconventional application of this super-fit scheme, where the super-fit individual is obtained by means of the Covariance Adaptation Matrix Evolution Strategy (CMA-ES), and fed to a single solution local search which perturbs iteratively each variable. Thus, compared to other super-fit schemes, the roles of super-fit individual generator and global optimizer are switched. To prevent premature convergence, the local search employs a re-sampling mechanism which inherits parts of the best individual while randomly sampling the remaining variables. We refer to such local search as Re-sampled Inheritance Search (RIS). Tested on the CEC 2013 optimization benchmark, the proposed algorithm, named CMA-ES-RIS, displays a respectable performance and a good balance between exploration and exploitation, resulting into a versatile and robust optimization tool.

This paper proposes an algorithm to solve the CEC2013 benchmark. The algorithm, namely Super-fit Multicriteria Adaptive Differential Evolution (SMADE), is a Memetic Computing approach based on the hybridization of two algorithmic schemes according to a super-fit memetic logic. More specifically, the Covariance Matrix Adaptive Evolution Strategy (CMAES), run at the beginning of the optimization process, is used to generate a solution with a high quality. This solution is then injected into the population of a modified Differential Evolution, namely Multicriteria Adaptive Differential Evolution (MADE). The improved solution is super-fit as it supposedly exhibits a performance a way higher than the other population individuals. The super-fit individual then leads the search of the MADE scheme towards the optimum. Unimodal or mildly multimodal problems, even when non-separable and ill-conditioned, tend to be solved during the early stages of the optimization by the CMAES. Highly multi-modal optimization problems are efficiently tackled by SMADE since the MADE algorithm (as well as other Differential Evolution schemes) appears to work very well when the search is led by a super-fit individual.

This paper introduces two lightweight variants of ISPO, a Single Particle Optimization algorithm recently proposed in the literature. The goal of this work is to improve upon the performance of the original ISPO, still bearing in mind its admirable algorithmic simplicity. The first variant, namely ISPOrestart, combines in a memetic fashion the logics of ISPO with a partial restart mechanism similar to the binomial crossover typically used in Differential Evolution. The second variant, named VISPO, builds on top of the restart process a very simple learning stage which tries to adapt the algorithm behaviour to the (non)-separability of the problem. Numerical results obtained on three complete optimization benchmarks show that not only the two algorithms are able to improve, incrementally, upon the performance of ISPO, but also they show respectable performance in comparison with modern complex state-of-the-art methods, especially when the problem dimensionality increases.

This paper proposes a novel implementation of memetic structure for continuous optimization problems. The proposed algorithm, namely Differential Evolution with Concurrent Fitness Based Local Search (DEcfbLS), enhances the DE performance by including a local search concurrently applied on multiple individuals of the population. The selection of the individuals undergoing local search is based on a fitness-based adaptive rule. The most promising individuals are rewarded with a local search operator that moves along the axes and complements the normal search moves of DE structure. The application of local search is performed with a shallow termination rule. This design has been performed in order to overcome the limitations within the search logic on the original DE algorithm. The proposed algorithm has been tested on various problems in multiple dimensions. Numerical results show that the proposed algorithm is promising candidate to take part to competition on Real-Parameter Single Objective Optimization at CEC-2013. A comparison against modern meta-heuristics confirms that the proposed algorithm robustly displays a good performance on the testbed under consideration.

Differential Evolution is a population based stochastic algorithm with less number of parameters to tune. However, the performance of DE is sensitive to the mutation and crossover strategies and their associated parameters. To obtain optimal performance, DE requires time consuming trial and error parameter tuning. To overcome the computationally expensive parameter tuning different adaptive/self-adaptive techniques have been proposed. Recently the idea of ensemble strategies in DE has been proposed and favorably compared with some of the state-of-the-art self-adaptive techniques. Compact Differential Evolution (cDE) is modified version of DE algorithm which can be effectively used to solve real world problems where sufficient computational resources are not available. cDE can be implemented on devices such as micro controllers or Graphics Processing Units (GPUs) which have limited memory. In this paper we introduced the idea of ensemble into cDE to improve its performance. The proposed algorithm is tested on the 30D version of 14 benchmark problems of Conference on Evolutionary Computation (CEC) 2005. The employment of ensemble strategies for the cDE algorithms appears to be beneficial and leads, for some problems, to competitive results with respect to the-state-of the-art DE based algorithms.

This paper proposes the compact differential evolution (cDE) algorithm. cDE, like other compact evolutionary algorithms, does not process a population of solutions but its statistic description which evolves similarly to all the evolutionary algorithms. In addition, cDE employs the mutation and crossover typical of differential evolution (DE) thus reproducing its search logic. Unlike other compact evolutionary algorithms, in cDE, the survivor selection scheme of DE can be straightforwardly encoded. One important feature of the proposed cDE algorithm is the capability of efficiently performing an optimization process despite a limited memory requirement. This fact makes the cDE algorithm suitable for hardware contexts characterized by small computational power such as micro-controllers and commercial robots. In addition, due to its nature cDE uses an implicit randomization of the offspring generation which corrects and improves the DE search logic. An extensive numerical setup has been implemented in order to prove the viability of cDE and test its performance with respect to other modern compact evolutionary algorithms and state-of-the-art population-based DE algorithms. Test results show that cDE outperforms on a regular basis its corresponding population-based DE variant. Experiments have been repeated for four different mutation schemes. In addition cDE outperforms other modern compact algorithms and displays a competitive performance with respect to state-of-the-art population-based algorithms employing a DE logic. Finally, the cDE is applied to a challenging experimental case study regarding the on-line training of a nonlinear neural-network-based controller for a precise positioning system subject to changes of payload. The main peculiarity of this control application is that the control software is not implemented into a computer connected to the control system but directly on the micro-controller. Both numerical results on the test functions and experimental results on the real-world problem are very promising and allow us to think that cDE and future developments can be an efficient option for optimization in hardware environments characterized by limited memory.

This paper is the part II of a paper composed of two parts. In the part I, a memetic approach consisting of applying a local search to the scale factor of a differential evolution framework in order to generate an off-spring with a high quality was proposed. The part II proposes the application of the scale factor local search within a differential evolution framework which integrates a self-adaptive update of the control parameters. In other words, unlike for the part I, the scale factor local search is applied to a an algorithmic framework characterized by multiple scale factors over the individuals of the population and scale factor updates during the evolution. Two simple local search logics have been tested, the first one employs the golden section search and the second one a hill-climber. The local search algorithms thus assist the global search and generates offspring with high performance which are subsequently supposed to promote the generation of better solutions within the evolutionary framework. Numerical results show that the hybridization is beneficial and able to outperform in many cases both the classical differential evolution and a self-adaptive differential evolution recently proposed in literature.

This paper proposes a modification of Differential Evolution (DE) schemes. During the offspring generation, a local search is applied, with a certain probability to the scale factor in order to generate an offspring with high performance. In a memetic fashion, the main idea in this paper is that the application of a different perspective in the search of a DE can assist the evolutionary framework and prevent the undesired effect of stagnation which DE is subject to. Two local search algorithms have been tested for this purpose and an application to the individual with the best performance has been proposed. The resulting algorithms seem to significantly enhance the performance of a standard DE scheme over a broad set of test problems. Numerical results show that the modified algorithm is very efficient with respect to a standard DE in terms of final solution detected, convergence speed and robustness.

This paper proposes the application of Memetic Algorithms employing Differential Evolution as an evolutionary framework in order to achieve optimal design of the control system for a permanent-magnet synchronous motor. Two Memetic Differential Evolution frameworks have been considered in this paper and their performance has been compared to a standard Differential Evolution, a standard Genetic Algorithm and a Memetic Algorithm presented in literature for solving the same problem. All the algorithms have been tested on a simulation of the whole system (control system and plant) using a model obtained through identification tests. Numerical results show that the Memetic Differential Evolution frameworks seem to be very promising in terms of convergence speed and has fairly good performance in terms of final solution detected for the real-world problem under examination. In particular, it should be remarked that the employment of a meta-heuristic local search component during the early stages of the evolution seems to be very beneficial in terms of algorithmic efficiency.

This paper aims to study the benefits and limitations in the hybridization of the differential evolution with local search algorithms. In order to perform this study, the performance of three memetic algorithms employing a differential evolution as an evolutionary framework and several local search algorithms adaptively coordinated by means of a fitness diversity logic have been analyzed. The performance of a standard differential evolution whose parameter setting has been executed only after fine tuning has also been taken into account in the comparison. The comparative analysis has been performed on a set of various test functions. Numerical results show that the memetic algorithms without any extensive parameter tuning are still competitive with the finely tuned plain differential evolution.

This paper proposes the employment of continuous probability distributions instead of step functions for adaptive coordination of the local search in fitness diversity based memetic algorithms. Two probability distributions are considered in this study: the beta and exponential distributions. These probability distributions have been tested within two memetic frameworks present in literature. Numerical results show that employment of the probability distributions can be beneficial and improve performance of the original memetic algorithms on a set of test functions without varying the balance between the evolutionary and local search components.

This article proposes an Enhanced Memetic Differential Evolution (EMDE) for designing digital filters which aim at detecting defects of the paper produced during an industrial process. Defect detection is handled by means of two Gabor filters and their design is performed by the EMDE. The EMDE is a novel adaptive evolutionary algorithm which combines the powerful explorative features of Differential Evolution with the exploitative features of three local search algorithms employing different pivot rules and neighborhood generating functions. These local search algorithms are the Hooke Jeeves Algorithm, a Stochastic Local Search, and Simulated Annealing. The local search algorithms are adaptively coordinated by means of a control parameter that measures fitness distribution among individuals of the population and a novel probabilistic scheme. Numerical results confirm that Differential Evolution is an efficient evolutionary framework for the image processing problem under investigation and show that the EMDE performs well. As a matter of fact, the application of the EMDE leads to a design of an efficiently tailored filter. A comparison with various popular metaheuristics proves the effectiveness of the EMDE in terms of convergence speed, stagnation prevention, and capability in detecting solutions having high performance.

This paper studies the problem of the optimal control design of permanent magnet synchronous motor (PMSM) drives taking into account the noise due to sensors and measurement devices. The problem is analyzed by means of an experimental approach which considers noisy data returned by the real plant (on-line). In other words, each fitness evaluation does not come from a computer but from a real laboratory experiment. In order to perform the optimization notwithstanding presence of the noise, this paper proposes an Adaptive Prudent- Daring Evolutionary Algorithm (APDEA). The APDEA is an evolutionary algorithm with a dynamic parameter setting. Furthermore, the APDEA employs a dynamic penalty term and two cooperative-competitive survivor selection schemes. The numerical results show that the APDEA robustly executes optimization in the noisy environment. In addition, comparison with other meta-heuristics shows that behavior of the APDEA is very satisfactory in terms of convergence velocity. A statistical test confirms the effectiveness of the APDEA.

This paper compares three different fitness diversity adaptations in multimeme algorithms (MmAs). These diversity indexes have been integrated within a MmA present in literature, namely fast adaptive memetic algorithm. Numerical results show that it is not possible to establish a superiority of one of these adaptive schemes over the others and choice of a proper adaptation must be made by considering features of the problem under study. More specifically, one of these adaptations outperforms the others in the presence of plateaus or limited range of variability in fitness values, another adaptation is more proper for landscapes having distant and strong basins of attraction, the third one, in spite of its mediocre average performance can occasionally lead to excellent results.

This paper proposes a period representation for modeling the multidrug HIV therapies and an Adaptive Multimeme Algorithm (AMmA) for designing the optimal therapy. The period representation offers benefits in terms of flexibility and reduction in dimensionality compared to the binary representation. The AMmA is a memetic algorithm which employs a list of three local searchers adaptively activated by an evolutionary framework. These local searchers, having different features according to the exploration logic and the pivot rule, have the role of exploring the decision space from different and complementary perspectives and, thus, assisting the standard evolutionary operators in the optimization process. Furthermore, the AMmA makes use of an adaptation which dynamically sets the algorithmic parameters in order to prevent stagnation and premature convergence. The numerical results demonstrate that the application of the proposed algorithm leads to very efficient medication schedules which quickly stimulate a strong immune response to HIV. The earlier termination of the medication schedule leads to lesser unpleasant side effects for the patient due to strong antiretroviral therapy. A numerical comparison shows that the AMmA is more efficient than three popular metaheuristics. Finally, a statistical test based on the calculation of the tolerance interval confirms the superiority of the AMmA compared to the other methods for the problem under study.

A fast adaptive memetic algorithm (FAMA) is proposed which is used to design the optimal control system for a permanent-magnet synchronous motor. The FAMA is a memetic algorithm with a dynamic parameter setting and two local searchers adaptively launched, either one by one or simultaneously, according to the necessities of the evolution. The FAMA has been tested for both offline and online optimization. The former is based on a simulation of the whole system--control system and plant--using a model obtained through identification tests. The online optimization is model free because each fitness evaluation consists of an experimental test on the real motor drive. The proposed algorithm has been compared with other optimization approaches, and a matching analysis has been carried out offline and online. Excellent results are obtained in terms of optimality, convergence, and algorithmic efficiency. Moreover, the FAMA has given very robust results in the presence of noise in the experimental system.