Convolutional neural networks (CNNs) trained on object recognition achieve high task performance but continue to exhibit vulnerability under a range of visual perturbations and out-of-domain images, when compared with biological vision. Prior work has demonstrated that coupling a standard CNN with a front-end (VOneBlock) that mimics the primate primary visual cortex (V1) can improve overall model robustness. Expanding on this, we introduce Early Vision Networks (EVNets), a new class of hybrid CNNs that combine the VOneBlock with a novel SubcorticalBlock, whose architecture draws from computational models in neuroscience and is parameterized to maximize alignment with subcortical responses reported across multiple experimental studies. Without being optimized to do so, the assembly of the SubcorticalBlock with the VOneBlock improved V1 alignment across most standard V1 benchmarks, and better modeled extra-classical receptive field phenomena. In addition, EVNets exhibit stronger emergent shape bias and outperform the base CNN architecture by 9.3\% on an aggregate benchmark of robustness evaluations, including adversarial perturbations, common corruptions, and domain shifts. Finally, we show that EVNets can be further improved when paired with a state-of-the-art data augmentation technique, surpassing the performance of the isolated data augmentation approach by 6.2\% on our robustness benchmark. This result reveals complementary benefits between changes in architecture to better mimic biology and training-based machine learning approaches.

The operation of hybrid networks (wireless and wired-based) is subject to a number of significant challenges, particularly in relation to the frequent changes in topology and high mobility that are inherent to them. This is especially the case in Vehicle to Everything (V2X) networks. This paper proposes a Software Defined Network (SDN)-based monitoring platform, designed for improving network visibility and responsiveness in dynamic environments. The proposed approach leverages Cooperative Intelligent Transportation System (C-ITS) messages to enable real-time tracking of vehicular mobility and wireless links quality, which enhances the SDN controller's ability to adapt to rapidly changing network conditions, thereby providing crucial data for informed decision-making. This broader view of the network provides the foundation for future seamless communication devices. The system's efficiency in maintaining up-to-date network awareness, optimizing handover processes, and ensuring communication stability across hybrid networks has been demonstrated in outdoor testing. The results show that incorporating the monitoring and control approaches within SDN environments markedly enhances the management and reliability of dynamic wireless networks.

Recently, it has been shown that simulating computations in early primate visual areas, up to the primary visual cortex (V1), at the front of convolutional neural networks (CNNs) leads to improvements in robustness to image corruptions. However, it remains unclear whether this improvement requires precisely matching the receptive field (RF) properties of V1 neurons or if some aspects are sufficient. Here, we explore this question by building several variants of a CNN model with a front-end modeling the primate V1 using a classical neuroscientific model, a Gabor Filter Bank (GFB) followed by simple- and complex- cell nonlinearities. Each model variant had varying levels of biological detail according to how the RF properties were sampled. The model variant sampling these parameters according to empirical biological distributions was considerably more robust to image corruptions than the variant sampling the parameters uniformly and independently (relative difference of 8.72%). However, a uniform variant capturing correlations between some GFB parameters obtained the same performance as the biological sampling variant. Our results show that it is not sufficient to approximate V1 with only the right class of function and parameter range, as it is also required to include the observed correlations between RF properties. However, it is not necessary to fully replicate the empirical distributions of V1 RF properties to obtain the desired improvement in robustness.

Adversarial examples are often cited by neuroscientists and machine learning researchers as an example of how computational models diverge from biological sensory systems. Recent work has proposed adding biologically-inspired components to visual neural networks as a way to improve their adversarial robustness. One surprisingly effective component for reducing adversarial vulnerability is response stochasticity, like that exhibited by biological neurons. Here, using recently developed geometrical techniques from computational neuroscience, we investigate how adversarial perturbations influence the internal representations of standard, adversarially trained, and biologically-inspired stochastic networks. We find distinct geometric signatures for each type of network, revealing different mechanisms for achieving robust representations. Next, we generalize these results to the auditory domain, showing that neural stochasticity also makes auditory models more robust to adversarial perturbations. Geometric analysis of the stochastic networks reveals overlap between representations of clean and adversarially perturbed stimuli, and quantitatively demonstrate that competing geometric effects of stochasticity mediate a tradeoff between adversarial and clean performance. Our results shed light on the strategies of robust perception utilized by adversarially trained and stochastic networks, and help explain how stochasticity may be beneficial to machine and biological computation.

Current state-of-the-art object recognition models are largely based on convolutional neural network (CNN) architectures, which are loosely inspired by the primate visual system. However, these CNNs can be fooled by imperceptibly small, explicitly crafted perturbations, and struggle to recognize objects in corrupted images that are easily recognized by humans. Here, by making comparisons with primate neural data, we first observed that CNN models with a neural hidden layer that better matches primate primary visual cortex (V1) are also more robust to adversarial attacks. Inspired by this observation, we developed VOneNets, a new class of hybrid CNN vision models. Each VOneNet contains a fixed weight neural network front-end that simulates primate V1, called the VOneBlock, followed by a neural network back-end adapted from current CNN vision models. The VOneBlock is based on a classical neuroscientific model of V1: the linear-nonlinear-Poisson model, consisting of a biologically-constrained Gabor filter bank, simple and complex cell nonlinearities, and a V1 neuronal stochasticity generator. After training, VOneNets retain high ImageNet performance, but each is substantially more robust, outperforming the base CNNs and state-of-the-art methods by 18% and 3%, respectively, on a conglomerate benchmark of perturbations comprised of white box adversarial attacks and common image corruptions. Finally, we show that all components of the VOneBlock work in synergy to improve robustness. While current CNN architectures are arguably brain-inspired, the results presented here demonstrate that more precisely mimicking just one stage of the primate visual system leads to new gains in ImageNet-level computer vision applications.

Soft biometrics have been emerging to complement other traits and are particularly useful for poor quality data. In this paper, we propose an efficient algorithm to estimate human head poses and to infer soft biometric labels based on the 3D morphology of the human head. Starting by considering a set of pose hypotheses, we use a learning set of head shapes synthesized from anthropometric surveys to derive a set of 3D head centroids that constitutes a metric space. Next, representing queries by sets of 2D head landmarks, we use projective geometry techniques to rank efficiently the joint 3D head centroids/pose hypotheses according to their likelihood of matching each query. The rationale is that the most likely hypotheses are sufficiently close to the query, so a good solution can be found by convex energy minimization techniques. Once a solution has been found, the 3D head centroid and the query are assumed to have similar morphology, yielding the soft label. Our experiments point toward the usefulness of the proposed solution, which can improve the effectiveness of face recognizers and can also be used as a privacy-preserving solution for biometric recognition in public environments.

Wearable vital signals monitoring systems are promoting new assistance approaches in the healthcare system and are essential for the future connected health paradigm. The present work addresses the design of a cardiac and coronary monitoring system taking into consideration dependability and autonomy issues. A fuzzy logic approach is used to determine, in case deviations in the captured electrocardiogram are detected, whether these are occurring in the patient or in the system. As for autonomy, the use of data compression versus extra data processing balance is analysed to find operating conditions for which compression is worth to be used.

This paper considers frequency-domain receiver design for OQPSK-type schemes. Since the I-Q interference can lead to significant performance degradation we propose an FDE design (frequency-domain equalization) where there is no I-Q interference in the sampling instants for the predominant OQPSK constellation. We also propose iterative FDEs with I-Q interference cancelation, as well as the cancelation of unintended OQPSK components.