With the growing adoption of machine learning systems in high-stakes domains such as healthcare, finance, and public administration, ensuring that these systems behave responsibly has become an urgent concern. Initiatives such as the EU AI Act and the broader movement toward responsible AI have highlighted fairness as a key challenge in the development and deployment of such technologies. Although existing tools support model optimization through hyperparameter tuning and algorithm selection, they often neglect the broader pipeline, overlooking how factors like data bias and model evaluation practices contribute to fairness. This paper presents Fairforge, a tool designed to support responsible ML development by guiding users through essential stages of the pipeline. These include data preprocessing with bias-awareness, fairness-informed model training, and postprocessing correction techniques. Fairforge also provides integrated interfaces for evaluating both performance and fairness metrics. The tool aims to make state-of-the-art fairness techniques accessible to users without deep expertise in the field. To validate the effectiveness of Fairforge, we conducted a series of usability tests involving users with diverse levels of technical backgrounds. The results demonstrate that the tool helps promote fairness in model development, even among non-expert practitioners.

The increasing deployment of Artificial Intelligence across various domains has led to a significant rise in power consumption, raising environmental concerns, and highlighting the need for energy-efficient algorithms and hardware. Machine Learning models – particularly Deep Convolutional Neural Networks and Large Language Models – demand substantial computational resources, contributing to higher carbon emissions and reduced sustainability. This work tackles the issue of energy consumption in Machine Learning, with a specific focus on inference. The proposed methodology leverages Neuroevolution to construct effective models while minimizing power usage. This work proposes a novel approach that trains two models simultaneously in a single process, explicitly encouraging one to consume less power without substantially compromising accuracy. It also proposes a mutation strategy that reinserts layer modules with a preference for power-efficient components. This approach is validated in two scenarios using the Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets: (i) evolving models from scratch, and (ii) optimizing pre-trained models for energy efficiency. When evolving from scratch, this method reduces power consumption by up to 49% with only a 2% accuracy drop on Fashion-MNIST, achieves a 20% power reduction on CIFAR-10 while improving accuracy by 0.8%, and enhances accuracy by 12.8% on CIFAR-100 while reducing power usage by 4%. For pre-trained models, this work achieves a 19.8% reduction in power usage on Fashion-MNIST with minimal accuracy loss, a 47% reduction on CIFAR-10 at the cost of a 7.7% drop in accuracy, and a 21.2% power saving on CIFAR-100 despite a 27.2% performance decline.

People with Type 1 diabetes need to predict their blood glucose levels regularly to keep them within a safe range. Accurate predictions help prevent short-term issues like hypoglycemia and reduce the risk of long-term complications. Evolutionary algorithms have shown potential for this task by generating reliable models for glucose prediction.

In nature, survival poses small benefits if one fails to reproduce and spread one's genes. This is particularly relevant in sexually reproductive species, which exerts another pressure dimension on the individual beyond natural selection: Sexual Selection. More often than not, the quality of the chosen mate is a crucial step in reproduction, making all the investment in mate choice worthwhile. This partly explains why partners often prefer certain secondary traits, such as ornaments, particularly if such traits signal good fitness. We hypothesize that the dynamics between mating preferences and fitness-dependent ornaments can act as a filter to find a mate within a population, exploiting good solutions while maintaining high diversity. In this work, we propose a new selection method for Genetic Programming based on these premises, validating our approach on regression problems. Results show that high levels of diversity are maintained when compared against a standard tournament selection with performance gains, reducing the overall error by 16.3% and 13.8% in training and testing respectively, and performing up to par with state-of-the-art Lexicase selection while also providing the best overall solution.

Deep Neural Networks (DNNs) have been successfully applied to a wide range of problems. However, two main limitations are commonly pointed out. The first one is that they require long time to design. The other is that they heavily rely on labelled data, which can sometimes be costly and hard to obtain. In order to address the first problem, neuroevolution has been proved to be a plausible option to automate the design of DNNs. As for the second problem, self-supervised learning has been used to leverage unlabelled data to learn representations. Our goal is to study how neuroevolution can help self-supervised learning to bridge the gap to supervised learning in terms of performance. In this work, we propose a framework that is able to evolve deep neural networks using self-supervised learning. Our results on the CIFAR-10 dataset show that it is possible to evolve adequate neural networks while reducing the reliance on labelled data. Moreover, an analysis to the structure of the evolved networks suggests that the amount of labelled data fed to them has less effect on the structure of networks that learned via self-supervised learning, when compared to individuals that relied on supervised learning.

To address the problem that existing quantum image watermarking schemes have only a single watermarking mode with weak robustness, in this paper we propose a novel multi-modal quantum watermarking (MMQW) scheme using the generalized model of novel enhanced quantum representation. Our scheme provides four quantum watermarking modes (G_G, G_C, C_C, C_G), covering both types of grayscale and color images for the watermark and the carrier image. To enhance the robustness, we propose the Block Bit-plane Centrosymmetric Expansion (BBCE) method, which utilizes controlled quantum gates to extend the watermark, making our method resistant to noise and geometric attacks. Moreover, we propose a Brightness-based Watermarking Mechanism (BWM) for embedding and extraction. By uniform embedding, BWM not only minimizes the impact on the carrier image but also reduces the visual distortion of the extracted watermark. In the proposed MMQW, we implement three adaptive embedding strategies using controlled quantum gates, each of which is adaptively triggered according to the corresponding modalities. Detailed quantum circuits for quantum computing are provided. To evaluate imperceptibility and robustness of the MMQW, we conduct experiments using high-resolution images from the USC-SIPI dataset. The results show that PSNR of the watermarked image ranges from 36 dB to 56 dB, indicating the high visual quality. The PSNR of the extracted watermark is about 34 dB when the noise density is 0.05, while the PSNR is higher than 48 dB under common quantum rotation attacks, which indicate the high robustness against noise addition and geometric attacks. In addition, the proposed MMQW can resist to cropping attack with cropping percentage up to 55%. A comprehensive comparison with existing state-of-the-art works shows that our method has significant advantages.

Grammar-Guided Genetic Programming (GGGP) employs a variety of concepts from evolutionary theory to autonomously design solutions for a given task. Recent insights from evolutionary biology can lead to further improvements in GGGP algorithms. In this paper, we propose a new mutation approach called Facilitated Mutation (FM) that is based on the theory of Facilitated Variation. We evaluate the performance of FM on the evolution of neural network optimizers for image classification, a relevant task in Evolutionary Computation, with important implications for the field of Machine Learning. We compare FM and FM combined with crossover (FMX) against a typical mutation approach to assess the benefits of the approach. We find that FMX provides statistical improvements in key metrics, creating a superior optimizer overall (+0.5% average test accuracy), improving the average quality of solutions (+53% average population fitness), and discovering more diverse high-quality behaviors (+523 high-quality solutions discovered on average). Additionally, FM and FMX reduce the number of fitness evaluations in an evolutionary run, reducing computational costs. FM's implementation cost is minimal and the approach is theoretically applicable to any algorithm where genes are associated witha grammar non-terminal, making this approach applicable in many existing GGGP systems.

The grammars used in grammar-based Genetic Programming (GP) methods have a significant impact on the quality of the solutions generated since they define the search space by restricting the solutions to its syntax. In this work, we propose Probabilistic Structured Grammatical Evolution (PSGE), a new approach that combines the Structured Grammatical Evolution (SGE) and Probabilistic Grammatical Evolution (PGE) representation variants and mapping mechanisms. The genotype is a set of dynamic lists, one for each non-terminal in the grammar, with each element of the list representing a probability used to select the next Probabilistic Context-Free Grammar (PCFG) derivation rule. PSGE statistically outperformed Grammatical Evolution (GE) on all six benchmark problems studied. In comparison to PGE, PSGE outperformed 4 of the 6 problems analyzed.

There has been growing development of co-creative systems for game design, where both humans and computers work as colleagues, proactively contributing with creative input. However, the collaborative process is still not as seamless as in human-human co-creativity. A key element still underdeveloped in these approaches is the communication between the human and the machine, which can be facilitated by providing the computational agent with explanatory capabilities. Based on principles of explainability for co-creative systems from previous literature, we propose a framework of explainability specifically applied to mixed-initiative scenarios in game design. We illustrate the applications of the framework by suggesting possible solutions adapted to different use cases of existing approaches and, additionally, of our own proposed approach.

This work proposes an extension to Structured Grammatical Evolution (SGE) called Co-evolutionary Probabilistic Structured Grammatical Evolution (Co-PSGE). In Co-PSGE each individual in the population is composed by a grammar and a genotype, which is a list of dynamic lists, each corresponding to a non-terminal of the grammar containing real numbers that correspond to the probability of choosing a derivation rule. Each individual uses its own grammar to map the genotype into a program. During the evolutionary process, both the grammar and the genotype are subject to variation operators.

The recent popularity of creative coding tools and Computational Creativity approaches are promoting a paradigm shift in the creation, development and production of Graphic Design artefacts. In this work, we present an evolutionary system for the automatic typesetting of typographic posters. This system is inspired by the letterpress typesetting process of the print houses in the earlier 19th century and employs lexicon-based approaches to recognise the semantic meaning of the posters’ content. During the evolutionary process, poster designs are automatically created and evaluated according to three objectives: legibility, aesthetics, and semantics. The system allows the users to express their preferences by specifying the intended visual features for the output designs, selecting the preferable fitness assignment strategy, and controlling different aspects of the evaluation strategy. We implemented three automatic strategies to evaluate the fitness of the posters: a multi-criteria hardwired fitness function, a multi-objective optimisation approach, and a hybrid strategy that combines features from the previous two strategies. The experimental results demonstrate the ability of the presented system to generate typographic posters, from scratch, and show the impact of the different evaluation strategies on the evolved poster designs. Overall, this research reveals how Evolutionary Computation approaches can be employed to develop novel co-creative typesetting tools and enable the automatic creation of customised typographic designs.

Genetic Programming (GP) is known to suffer from the burden of being computationally expensive by design. While, over the years, many techniques have been developed to mitigate this issue, data vectorization, in particular, is arguably still the most attractive strategy due to the parallel nature of GP. In this work, we employ a series of benchmarks meant to compare both the performance and evolution capabilities of different vectorized and iterative implementation approaches across several existing frameworks. Namely, TensorGP, a novel open-source engine written in Python, is shown to greatly benefit from the TensorFlow library to accelerate the domain evaluation phase in GP. The presented performance benchmarks demonstrate that the TensorGP engine manages to pull ahead, with relative speedups above two orders of magnitude for problems with a higher number of fitness cases. Additionally, as a consequence of being able to compute larger domains, we argue that TensorGP performance gains aid the discovery of more accurate candidate solutions.

Automatic fraud detection and prevention are challenging problems that have attracted the attention of many researchers in academia and industry. Over the last few years, many improvements have been achieved, especially in predictive models based on Machine Learning. However, a considerable amount of these models only provide a prediction score and a short explanation which may not be enough to make informed decisions. This paper presents a visualization tool that aims to assist fraud analysts in making informed decisions and increase their effectiveness in the detection of fraud. To this end, we designed three visualisation models that apply state of the art techniques to support the analysis of fraudulent transactions. To demonstrate the analytic capabilities and benefits of the proposed tool, we discussed a real use case scenario and conducted user testing with real fraud analysts. Through the feedback from both studies, we were able to conclude that the tool is an asset to facilitate the detection of suspicious events as well to improve the analysis times of the fraud analysts’ work process.

The choice of a proper learning rate is paramount for good Artificial Neural Network training and performance. In the past, one had to rely on experience and trial-and-error to find an adequate learning rate. Presently, a plethora of state of the art automatic methods exist that make the search for a good learning rate easier. While these techniques are effective and have yielded good results over the years, they are general solutions. This means the optimization of learning rate for specific network topologies remains largely unexplored. This work presents AutoLR, a framework that evolves Learning Rate Schedulers for a specific Neural Network Architecture using Structured Grammatical Evolution. The system was used to evolve learning rate policies that were compared with a commonly used baseline value for learning rate. Results show that training performed using certain evolved policies is more efficient than the established baseline and suggest that this approach is a viable means of improving a neural network's performance.

Generative adversarial networks (GANs) achieved relevant advances in the field of generative algorithms, presenting high-quality results mainly in the context of images. However, GANs are hard to train, and several aspects of the model should be previously designed by hand to ensure training success. In this context, evolutionary algorithms such as COEGAN were proposed to solve the challenges in GAN training. Nevertheless, the lack of diversity and premature optimization can be found in some of these solutions. We propose in this paper the application of a quality-diversity algorithm in the evolution of GANs. The solution is based on the Novelty Search with Local Competition (NSLC) algorithm, adapting the concepts used in COEGAN to this new proposal. We compare our proposal with the original COEGAN model and with an alternative version using a global competition approach. The experimental results evidenced that our proposal increases the diversity of the discovered solutions and leverage the performance of the models found by the algorithm. Furthermore, the global competition approach was able to consistently find better models for GANs.

Temporal datasets are a product of many scientific disciplines and analyzing the events that they describe may help provide valuable insight into their respective research subjects and help move towards solutions to existing problems. Time-series analysis is still an open problem which prompts new solutions, particularly the discovery of patterns across complex temporal networks. Visualization has proven to be a valuable tool in the analysis of such datasets, with the emergence of new models such as Time Curves, which distorts timelines to position time points based on their similarity, creating visualizations that highlight behavior patterns. In this paper, we further explore time-series functionally and aesthetically by revising the dynamic Time Curves models in CroP, a visualization tool with coordinated multiple views. Firstly, we propose the additional of new visual elements and interactive functions, coordinated with a network visualization to help discover and understand temporal patterns across complex datasets. Secondly, we visually explore time-series through Time Paths, a parameter-based force-directed layout that can dynamically transform the original model to either highlight small data variations or reduce visual noise in favor of overall patterns.

To analyse and detect fraudulent patterns in banking transactions, most fraud analysts use spreadsheets which makes the overall process time-consuming and complex. In this article, we propose a visualization tool that aims to ease the analysis of banking transactions over time and the detection of the transactions' topology and of suspicious behaviours. Our main contributions are: (i) a user-centred visual tool, developed with the aid of fraud experts; (ii) a method that characterises the transactions topology through a self-organising algorithm; (iii) the visual characterisation of transactions through complex glyphs; and (iv) a user study to assess the tool effectiveness.

The field of Information Visualization has undergone major changes in the last decades due to the growing computational power and easier access to various technologies by a greater number of people. However, Information Visualization and its techniques literacy continue to be a knowledge associated to a reduced audience. In order to surpass this condition of Information Visualization, new practitioners have applied techniques from other areas, such as the arts, to develop visualizations that could transmit information in a more casual and accessible way to a larger number of people, weighing heavily on the artistic component. In this paper, we present a visualization that portrays information about public contracts held in Portugal, that despite being public data, is not analyzed or much less visualized by the majority. To do so we taken a casual representation approach with a strong aesthetics component in mind with the objective of promoting awareness about the dimension and distribution of the money applied daily throughout Portugal. We perform a phenomenological experiment to assess the effectiveness of our work in transmitting the information and evoking the desired insights. The experiment allowed us to collect distinct interpretations that could lead to further approaches and improvements in future iterations.

Portraits of No One is an internet artwork that generates and displays artificial photo-realistic portraits of human faces. This artwork assumes the form of a web page that synthesises new portraits by automatically recombining the facial features of the users who interacted with it. The generated portraits invoke the capabilities of Artificial Intelligence to generate visual content that makes people question themselves about the veracity of what they are seeing.

SUMMARY: CroP is a data visualization application that focuses on the analysis of relational data that changes over time. While it was specifically designed for addressing the preeminent need to interpret large scale time series from gene expression studies, CroP is prepared to analyze datasets from multiple contexts. Multiple datasets can be uploaded simultaneously and viewed through dynamic visualization models, which are contained within flexible panels that allow users to adapt the workspace to their data. Through clustering and the time curve visualization it is possible to quickly identify groups of data points with similar proprieties or behaviors, as well as temporal patterns across all points, such as periodic waves of expression. Additionally, it integrates a public biomedical database for gene annotation. CroP will be of major interest to biologists who seek to extract relations from complex sets of data. AVAILABILITY AND IMPLEMENTATION: CroP is freely available for download as an executable jar at https://cdv.dei.uc.pt/crop/.

Generative adversarial networks (GAN) present state-of-the-art results in the generation of samples following the distribution of the input dataset. However, GANs are difficult to train, and several aspects of the model should be previously designed by hand. Neuroevolution is a well-known technique used to provide the automatic design of network architectures which was recently expanded to deep neural networks.

The field of computational biology has become largely dependent on data visualization tools to analyze the increasing quantities of data gathered through the use of new and growing technologies. Aside from the volume, which often results in large amounts of noise and complex relationships with no clear structure, the visualization of biological data sets is hindered by their heterogeneity, as data are obtained from different sources and contain a wide variety of attributes, including spatial and temporal information. This requires visualization approaches that are able to not only represent various data structures simultaneously but also provide exploratory methods that allow the identification of meaningful relationships that would not be perceptible through data analysis algorithms alone. In this article, we present a survey of visualization approaches applied to the analysis of biological data. We focus on graph-based visualizations and tools that use coordinated multiple views to represent high-dimensional multivariate data, in particular time series gene expression, protein-protein interaction networks and biological pathways. We then discuss how these methods can be used to help solve the current challenges surrounding the visualization of complex biological data sets.

Developing learning systems is challenging in many ways: often there is the need to optimise the learning algorithm structure and parameters, and it is necessary to decide which is the best data representation to use, i.e., we usually have to design features and select the most representative and useful ones. In this work we focus on the later and investigate whether or not it is possible to obtain good performances with compressed versions of the original data, possibly reducing the learning time. The process of compressing the data, i.e., reducing its dimensionality, is typically conducted by someone who has domain knowledge and expertise, and engineers features in a trial-and-error endless cycle. Our goal is to achieve such compressed versions automatically; for that, we use an Evolutionary Algorithm to generate the structure of AutoEncoders. Instead of targeting the reconstruction of the images, we focus on the reconstruction of the mean signal of each class, and therefore the goal is to acquire the most representative characteristics of each class. Results on the MNIST dataset show that the proposed approach can not only reduce the original dataset dimensionality, but the performance of the classifiers over the compressed representation is superior to the performance on the original uncompressed images.

Visualization models have shown to be remarkably important in the interpretation of datasets across many fields of study. In the field of Biology, data visualization is used to better understand processes that range from phylogenetic trees to multiple layers of molecular networks. The latter is especially challenging due to the large quantities of varying elements and complex relationships, often with no perceptible structure. Although various tools have been proposed to improve the visualization of molecular networks, many challenges still persist. In this paper, we propose a tool that uses interactive visualization models to represent the dynamic behaviors of molecular networks. The tool employs various methods to explore and organize the data, including clustering, force-directed layouts, and a timeline for navigating through time-series data. To further analyze temporal attributes, the timeline can be distorted through a force-directed layout to spatially position time points according to their similarity. Additionally, gene expression can be annotated through an integrated biological database. The visualization model was validated with the use of time-series gene expression RNA-Seq data from the HIV-1 infection.

Despite some authors stating that data-relatedness helps interpretation, glyphs are often used unrelated to the represented data. In order to automatically produce data-related glyphs, a large visual repository is required, as well as, image structure suitable for data representation. In this paper, we propose a strategy that fulfills the two requirements and allows the production of glyphs related to the data thematic (literal and metaphorical). We compare used approach with current glyph techniques and discuss the results.

This project is about the creation of a music festival’s dynamic brand, which reacts to music and customises itself to any person participating in the event.

Through Data Visualisation and Sonification models, we present a study of multimodal representations to characterise the Portuguese consumption patterns, which were gathered from Portuguese hypermarkets and supermarkets over the course of two years. We focus on the rhythmic nature of the data to create and discuss audio and visual representations that highlight disruptions and sudden changes in the normal consumption patterns. For this study, we present two distinct visual and audio representations and discuss their strengths and limitations.

In the analysis of time-series, it is common to focus on the identification of changing behaviours and patterns that repeat over time. In this article, we propose a visualisation model based on a radial calendar to analyse the Portuguese's consumption data. The model is intended to assist the analysts within a Portuguese Retail Company in the identification of periodic patterns and deviations from the normal consumption values. Our main contributions are: (i) the representation and characterisation of the Portuguese's consumption behaviour over time; (ii) a radial visualisation model to identify consumption patterns and their deviations; and (iii) a user case study to compare this visualisation model to a regular calendar layout. Our model has as main requirement the representation of the maximum amount of data in one single space. As such, it is ideal for analysts without prior knowledge of the data, since it provides an effective and efficient qualitative overview of the Portuguese's consumption.

We present MixMash, an interactive tool to assist users in the creation of music mashups based on cross-modal associations between musical content analysis and information visualisation. Our point of departure is a harmonic mixing method for musical mashups by Bernardes et al. [1]. To surpass design limitations identified in the previous method, we propose a new interactive visualisation of multidimensional musical attributes-hierarchical harmonic compatibility, onset density, spectral region, and timbral similarity-extracted from a large collection of audio tracks. All tracks are represented as nodes whose distances and edge connections indicate their harmonic compatibility as a result of a force-directed graph. In addition, we provide a visual language that aims to enhance the tool usability and foster creative endeavour in the search for meaningful music mixes.

The effectiveness of Artificial Neural Networks (ANNs) depends on a non-trivial manual crafting of their topology and parameters. Typically, practitioners resort to a time consuming methodology of trial-and-error to find and/or adjust the models to solve specific tasks. To minimise this burden one might resort to algorithms for the automatic selection of the most appropriate properties of a given ANN. A remarkable example of such methodologies is Grammar-based Genetic Programming. This work analyses and compares the use of two grammar-based methods, Grammatical Evolution (GE) and Structured Grammatical Evolution (SGE), to automatically design and configure ANNs. The evolved networks are used to tackle several classification datasets. Experimental results show that SGE is able to automatically build better models than GE, and that are competitive with the state of the art, outperforming hand-designed ANNs in all the used benchmarks.

Typography plays a key communication role in the contemporary information-dense culture. Type design is a central, complex, and time consuming task. In this work we develop the generative system to type design based on an evolutionary algorithm. The key novel contributions are twofold. First, in terms of representation it relies on the use of assemblages of shapes to form glyphs. There are no limitations to the types of shapes that can be used. Second, we explore a compromise between legibility and expressiveness, testing different automatic fitness assignment schemes. The attained results show that we are able to evolve a wide variety of alternative glyphs, making the proposed system a viable alternative for real-world applications in the field of type design.

Ant- and ant-colony-inspired ALife art is characterized by the artistic exploration of the emerging collective behavior of computational agents, developed using ants as a metaphor. We present a chronology that documents the emergence and history of such visual art, contextualize ant- and ant-colony-inspired art within generative art practices, and consider how it relates to other ALife art. We survey many of the algorithms that artists have used in this genre, address some of their aims, and explore the relationships between ant- and ant-colony-inspired art and research on ant and ant colony behavior.

In the past few years the use of semantic aware crossover and mutation has become a hot topic of research within the Genetic Programming community. Unlike traditional genetic operators that perform syntactic manipulations of programs regardless of their behavior, semantic driven operators promote direct search on the underlying behavioral space. Based on previous work on semantic Genetic Programming and Genetic Morphing, we propose and implement semantic driven crossover and mutation operators for evolutionary art. The experimental results focus on assessing how these operators compare with traditional ones.

Sexual Selection through Mate Choice has for the past few decades attracted the attention of many researchers from different fields. Numerous contributions and supporting evidence for the role and impact of Sexual Selection through Mate Choice in Evolution have emerged since then. Just like Evolutionary Theory has had to adapt its models to account for Sexual Selection through Mate Choice and its effects, it is relevant to study and analyse the impact that Mate Choice may have on Evolutionary Algorithms. In this study we describe a nature inspired self-adaptive Mate Choice approach designed to tackle Symbolic Regression problems. Results on a set of test functions are presented and compared to a standard approach, showing that Mate Choice is able to contribute to enhanced results on complex instances of Symbolic Regression. Also, the resulting behaviours are contrasted and discussed, suggesting that Mate Choice is able to evolve Mating evaluation functions that are able to select partners in meaningful and valuable ways.

Sexual Selection through Mate Choice has, over the past few decades, attracted the attention of researchers from various fields. They have gathered numerous supporting evidence, establishing Mate Choice as a major driving force of evolution, capable of shaping complex traits and behaviours. Despite its wide acceptance and relevance across various research fields, the impact of Mate Choice in Evolutionary Computation is still far from understood, both regarding performance and behaviour.

Island Models are parallel approaches to Evolutionary Algorithms that not only offer the benefits of parallelization but are also regarded as models with an extensively distinct behaviour. This study applies for the first time an Island Model to the optimization of short-ranged Morse clusters, combined with a hybrid steady-state evolutionary algorithm and a local optimization method. Different migration parameters are experimented and the resulting behaviours are extensively analysed. Results are compared to a state-of-the-art sequential approach, showing slight improvements. Differences in behaviour between the Island Model and the sequential approach are comprehensively discussed. This study shows that Island Models are a competitive parallel approach with promising results on cluster geometry optimization problems.

We introduce photogrowth, an evolutionary approach to the production of non-photorealistic renderings of images. The painting algorithm - inspired by ant colony approaches - is described and explained, giving emphasis to its novel aspects: the evolution of the sensory parameters of the ants; the production of resolution independent images; the rendering lines of variable width. The experimental results highlight the range of imagery that can be evolved by the system and show the potential of the approach for the production of large-format artworks.

The goal of this research is to analyze how individual learning interacts with an evolutionary algorithm in its search for best candidates for the Busy Beaver problem. To study this interaction, two learning models, implemented as local search procedures, are proposed. Experimental results show that, in highly irregular search spaces that are prone to premature convergence, local search methods are not an effective help to evolution. In addition, one interesting effect related to learning is reported: when the mutation rate is too high, learning acts as a repair, reintroducing some useful information that was lost.