CyberSec Research

Since soft robotics are composed of compliant materials, they perform better than conventional rigid robotics in specific fields, such as medical applications. However, the field of soft robotics is fairly new, and the design process of their morphology and their controller strategies has not yet been thoroughly studied. Consequently, here, an automated design method for the controller of soft actuators based on Neuroevolution is proposed. Specifically, the suggested techniques employ Neuroevolution of Augmenting Topologies (NEAT) and Hypercube-based NEAT (HyperNEAT) to generate the synchronization profile of the components of a simulated soft actuator by employing Compositional Pattern Producing Networks (CPPNs). As a baseline methodology, a Standard Genetic Algorithm (SGA) was used. Moreover, to test the robustness of the proposed methodologies, both high- and low-performing morphologies of soft actuators were utilized as testbeds. Moreover, the use of an affluent and a more limited set of activation functions for the Neuroevolution targets was tested throughout the experiments. The results support the hypothesis that Neuroevolution based methodologies are more appropriate for designing controllers that align with both types of morphologies. In specific, NEAT performed better for all different scenarios tested and produced more simplistic networks that are easier to implement in real life applications.

We introduce Perturbative Gradient Training (PGT), a novel training paradigm that overcomes a critical limitation of physical reservoir computing: the inability to perform backpropagation due to the black-box nature of physical reservoirs. Drawing inspiration from perturbation theory in physics, PGT uses random perturbations in the network's parameter space to approximate gradient updates using only forward passes. We demonstrate the feasibility of this approach on both simulated neural network architectures, including a dense network and a transformer model with a reservoir layer, and on experimental hardware using a magnonic auto-oscillation ring as the physical reservoir. Our results show that PGT can achieve performance comparable to that of standard backpropagation methods in cases where backpropagation is impractical or impossible. PGT represents a promising step toward integrating physical reservoirs into deeper neural network architectures and achieving significant energy efficiency gains in AI training.

Among the genetic algorithms generally used for optimization problems in the recent decades, quantum-inspired variants are known for fast and high-fitness convergence and small resource requirement. Here the application to the patient scheduling problem in proton therapy is reported. Quantum chromosomes are tailored to possess the superposed data of patient IDs and gantry statuses. Selection and repair strategies are also elaborated for reliable convergence to a clinically feasible schedule although the employed model is not complex. Clear advantage in population size is shown over the classical counterpart in our numerical results for both a medium-size test case and a large-size practical problem instance. It is, however, observed that program run time is rather long for the large-size practical case, which is due to the limitation of classical emulation and demands the forthcoming true quantum computation. Our results also revalidate the stability of the conventional classical genetic algorithm.

Spiking Neural Networks (SNNs) have emerged as a new generation of energy-efficient neural networks suitable for implementation on neuromorphic hardware. As neuromorphic hardware has limited memory and computing resources, weight pruning and quantization have recently been explored to improve SNNs' efficiency. State-of-the-art SNN pruning/quantization methods employ multiple compression and training iterations, increasing the cost for pre-trained or very large SNNs. In this paper, we propose a new one-shot post-training pruning/quantization framework, Optimal Spiking Brain Compression (OSBC), that adapts the Optimal Brain Compression (OBC) method of [Frantar, Singh, and Alistarh, 2023] for SNNs. Rather than minimizing the loss on neuron input current as OBC does, OSBC achieves more efficient and accurate SNN compression in one pass by minimizing the loss on spiking neuron membrane potential with a small sample dataset. Our experiments on neuromorphic datasets (N-MNIST, CIFAR10-DVS, DVS128-Gesture) demonstrate that OSBC can achieve 97% sparsity through pruning with 1.41%, 10.20%, and 1.74% accuracy loss, or 4-bit symmetric quantization with 0.17%, 1.54%, and 7.71% accuracy loss, respectively. Code will be available on GitHub.

Soft robots have proven to outperform traditional robots in applications related to propagation in geometrically constrained environments. Designing these robots and their controllers is an intricate task, since their building materials exhibit non-linear properties. Human designs may be biased; hence, alternative designing processes should be considered. We present a cooperative neuro coevolution approach to designing the morphologies of soft actuators and their controllers for applications in drug delivery apparatus. Morphologies and controllers are encoded as compositional pattern-producing networks evolved by Neuroevolution of Augmented Topologies (NEAT) and in cooperative coevolution methodology, taking into account different collaboration methods. Four collaboration methods are studied: n best individuals, n worst individuals, n best and worst individuals, and n random individuals. As a performance baseline, the results from the implementation of Age-Fitness Pareto Optimisation (AFPO) are considered. The metrics used are the maximum displacement in upward bending and the robustness of the devices in terms of applying to the same evolved morphology a diverse set of controllers. Results suggest that the cooperative neuro coevolution approach can produce more suitable morphologies for the intended devices than AFPO.

IntLevPy provides a comprehensive description of the IntLevPy Package, a Python library designed for simulating and analyzing intermittent and L\'evy processes. The package includes functionalities for process simulation, including full parameter estimation and fitting optimization for both families of processes, moment calculation, and classification methods. The classification methodology utilizes adjusted-$R^2$ and a noble performance measure {\Gamma}, enabling the distinction between intermittent and L\'evy processes. IntLevPy integrates iterative parameter optimization with simulation-based validation. This paper provides an in-depth user guide covering IntLevPy software architecture, installation, validation workflows, and usage examples. In this way, IntLevPy facilitates systematic exploration of these two broad classes of stochastic processes, bridging theoretical models and practical applications.

Rule representations significantly influence the search capabilities and decision boundaries within the search space of Learning Classifier Systems (LCSs), a family of rule-based machine learning systems that evolve interpretable models through evolutionary processes. However, it is very difficult to choose an appropriate rule representation for each problem. Additionally, some problems benefit from using different representations for different subspaces within the input space. Thus, an adaptive mechanism is needed to choose an appropriate rule representation for each rule in LCSs. This article introduces a flexible rule representation using a four-parameter beta distribution and integrates it into a fuzzy-style LCS. The four-parameter beta distribution can form various function shapes, and this flexibility enables our LCS to automatically select appropriate representations for different subspaces. Our rule representation can represent crisp/fuzzy decision boundaries in various boundary shapes, such as rectangles and bells, by controlling four parameters, compared to the standard representations such as trapezoidal ones. Leveraging this flexibility, our LCS is designed to adapt the appropriate rule representation for each subspace. Moreover, our LCS incorporates a generalization bias favoring crisp rules where feasible, enhancing model interpretability without compromising accuracy. Experimental results on real-world classification tasks show that our LCS achieves significantly superior test accuracy and produces more compact rule sets. Our implementation is available at https://github.com/YNU-NakataLab/Beta4-UCS. An extended abstract related to this work is available at https://doi.org/10.36227/techrxiv.174900805.59801248/v1.

The decision-making process significantly influences the predictions of machine learning models. This is especially important in rule-based systems such as Learning Fuzzy-Classifier Systems (LFCSs) where the selection and application of rules directly determine prediction accuracy and reliability. LFCSs combine evolutionary algorithms with supervised learning to optimize fuzzy classification rules, offering enhanced interpretability and robustness. Despite these advantages, research on improving decision-making mechanisms (i.e., class inference schemes) in LFCSs remains limited. Most LFCSs use voting-based or single-winner-based inference schemes. These schemes rely on classification performance on training data and may not perform well on unseen data, risking overfitting. To address these limitations, this article introduces a novel class inference scheme for LFCSs based on the Dempster-Shafer Theory of Evidence (DS theory). The proposed scheme handles uncertainty well. By using the DS theory, the scheme calculates belief masses (i.e., measures of belief) for each specific class and the ``I don't know'' state from each fuzzy rule and infers a class from these belief masses. Unlike the conventional schemes, the proposed scheme also considers the ``I don't know'' state that reflects uncertainty, thereby improving the transparency and reliability of LFCSs. Applied to a variant of LFCS (i.e., Fuzzy-UCS), the proposed scheme demonstrates statistically significant improvements in terms of test macro F1 scores across 30 real-world datasets compared to conventional voting-based and single-winner-based fuzzy inference schemes. It forms smoother decision boundaries, provides reliable confidence measures, and enhances the robustness and generalizability of LFCSs in real-world applications. Our implementation is available at https://github.com/YNU-NakataLab/jUCS.

This paper introduces SENMap, a mapping and synthesis tool for scalable, energy-efficient neuromorphic computing architecture frameworks. SENECA is a flexible architectural design optimized for executing edge AI SNN/ANN inference applications efficiently. To speed up the silicon tape-out and chip design for SENECA, an accurate emulator, SENSIM, was designed. While SENSIM supports direct mapping of SNNs on neuromorphic architectures, as the SNN and ANNs grow in size, achieving optimal mapping for objectives like energy, throughput, area, and accuracy becomes challenging. This paper introduces SENMap, flexible mapping software for efficiently mapping large SNN and ANN applications onto adaptable architectures. SENMap considers architectural, pretrained SNN and ANN realistic examples, and event rate-based parameters and is open-sourced along with SENSIM to aid flexible neuromorphic chip design before fabrication. Experimental results show SENMap enables 40 percent energy improvements for a baseline SENSIM operating in timestep asynchronous mode of operation. SENMap is designed in such a way that it facilitates mapping large spiking neural networks for future modifications as well.

We propose a new ternary spiking neuron model to improve the representation capacity of binary spiking neurons in deep Q-learning. Although a ternary neuron model has recently been introduced to overcome the limited representation capacity offered by the binary spiking neurons, we show that its performance is worse than that of binary models in deep Q-learning tasks. We hypothesize gradient estimation bias during the training process as the underlying potential cause through mathematical and empirical analysis. We propose a novel ternary spiking neuron model to mitigate this issue by reducing the estimation bias. We use the proposed ternary spiking neuron as the fundamental computing unit in a deep spiking Q-learning network (DSQN) and evaluate the network's performance in seven Atari games from the Gym environment. Results show that the proposed ternary spiking neuron mitigates the drastic performance degradation of ternary neurons in Q-learning tasks and improves the network performance compared to the existing binary neurons, making DSQN a more practical solution for on-board autonomous decision-making tasks.

Kolmogorov-Arnold Networks (KANs) uniquely combine high accuracy with interpretability, making them valuable for scientific modeling. However, it is unclear a priori how deep a network needs to be for any given task, and deeper KANs can be difficult to optimize. Here we introduce multi-exit KANs, where each layer includes its own prediction branch, enabling the network to make accurate predictions at multiple depths simultaneously. This architecture provides deep supervision that improves training while discovering the right level of model complexity for each task. Multi-exit KANs consistently outperform standard, single-exit versions on synthetic functions, dynamical systems, and real-world datasets. Remarkably, the best predictions often come from earlier, simpler exits, revealing that these networks naturally identify smaller, more parsimonious and interpretable models without sacrificing accuracy. To automate this discovery, we develop a differentiable "learning to exit" algorithm that balances contributions from exits during training. Our approach offers scientists a practical way to achieve both high performance and interpretability, addressing a fundamental challenge in machine learning for scientific discovery.

Artificial life aims to understand the fundamental principles of biological life by creating computational models that exhibit life-like properties. Although artificial life systems show promise for simulating biological evolution, achieving open-endedness remains a central challenge. This work investigates mechanisms to promote exploration and unbounded innovation within evolving populations of Lenia continuous cellular automata by evaluating individuals against each other with respect to distinctiveness, population sparsity, and homeostatic regulation. Multi-objective ranking of these intrinsic fitness objectives encourages the perpetual selection of novel and explorative individuals in sparse regions of the descriptor space without restricting the scope of emergent behaviors. We present experiments demonstrating the effectiveness of our multi-objective approach and emphasize that intrinsic evolution allows diverse expressions of artificial life to emerge. We argue that adaptive exploration improves evolutionary dynamics and serves as an important step toward achieving open-ended evolution in artificial systems.

The brain is made up of a vast set of heterogeneous regions that dynamically organize into pathways as a function of task demands. Examples of such pathways can be seen in the interactions between cortical and subcortical networks during learning. This raises the question of how exactly brain regions organize into these dynamic groups. In this work, we use an extension of the Heterogeneous Mixture-of-Experts architecture, to show that heterogeneous regions do not form processing pathways by themselves, implying that the brain likely implements specific constraints which result in reliable formation of pathways. We identify three biologically relevant inductive biases that encourage pathway formation: a routing cost imposed on the use of more complex regions, a scaling factor that reduces this cost when task performance is low, and randomized expert dropout. When comparing our resulting Mixture-of-Pathways model with the brain, we observe that the artificial pathways match how the brain uses cortical and subcortical systems to learn and solve tasks of varying difficulty. In summary, we introduce a novel framework for investigating how the brain forms task-specific pathways through inductive biases which may make Mixture-of-Experts architectures in general more adaptive.

Reinforcement Learning's high sensitivity to hyperparameters is a source of instability and inefficiency, creating significant challenges for practitioners. Hyperparameter Optimization (HPO) algorithms have been developed to address this issue, among them Population-Based Training (PBT) stands out for its ability to generate hyperparameters schedules instead of fixed configurations. PBT trains a population of agents, each with its own hyperparameters, frequently ranking them and replacing the worst performers with mutations of the best agents. These intermediate selection steps can cause PBT to focus on short-term improvements, leading it to get stuck in local optima and eventually fall behind vanilla Random Search over longer timescales. This paper studies how this greediness issue is connected to the choice of evolution frequency, the rate at which the selection is done. We propose Multiple-Frequencies Population-Based Training (MF-PBT), a novel HPO algorithm that addresses greediness by employing sub-populations, each evolving at distinct frequencies. MF-PBT introduces a migration process to transfer information between sub-populations, with an asymmetric design to balance short and long-term optimization. Extensive experiments on the Brax suite demonstrate that MF-PBT improves sample efficiency and long-term performance, even without actually tuning hyperparameters.

Charting the lifespan evolutionary trajectory of brain function serves as the normative standard for preventing mental disorders during brain development and aging. Although numerous MRI studies have mapped the structural connectome for young cohorts, the EEG-based functional connectome is unknown to characterize human lifespan, limiting its practical applications for the early detection of brain dysfunctions at the community level. This work aimed to undertake normative modeling from the perspective of EEG network topology. Frequency-dependent scalp EEG functional networks were constructed based on EEG cross-spectra aged 5-97 years from 9 countries and network characteristics were quantified. First, GAMLSS were applied to describe the normative curves of the network characteristics in different frequency bands. Subsequently, addressing the limitations of existing regression approaches for whole brain network analysis, this paper proposed an interpretable encoder-decoder framework, Generative Age-dependent brain Network nORmative Model (GANORM). Building upon this framework, we established an age-dependent normative trajectory of the complete brain network for the entire lifespan. Finally, we validated the effectiveness of the norm using EEG datasets from multiple sites. Subsequently, we evaluated the effectiveness of GANORM, and the tested performances of BPNN showed the R^2 was 0.796, the MAE was 0.081, and the RMSE was 0.013. Following established lifespan brain network norm, GANORM also exhibited good results upon verification using healthy and disease data from various sites. The deviation scores from the normative mean for the healthy control group were significantly smaller than those of the disease group.

Spiking Neural Networks have earned increased recognition in recent years owing to their biological plausibility and event-driven computation. Spiking neurons are the fundamental building components of Spiking Neural Networks. Those neurons act as computational units that determine the decision to fire an action potential. This work presents a methodology to implement biologically plausible yet scalable spiking neurons in hardware. We show that it is more efficient to design neurons that mimic the $I_{Na,p}+I_{K}$ model rather than the more complicated Hodgkin-Huxley model. We demonstrate our methodology by presenting eleven novel minimal spiking neuron circuits in Parts I and II of the paper. We categorize the neuron circuits presented into two types: Resonators and Integrators. We discuss the methodology employed in designing neurons of the resonator type in Part I, while we discuss neurons of the integrator type in Part II. In part I, we postulate that Sodium channels exhibit type-N negative differential resistance. Consequently, we present three novel minimal neuron circuits that use type-N negative differential resistance circuits or devices as the Sodium channel. Nevertheless, the aim of the paper is not to present a set of minimal neuron circuits but rather the methodology utilized to construct those circuits.

A random-key genetic algorithm is an evolutionary metaheuristic for discrete and global optimization. Each solution is encoded as a vector of N random keys, where a random key is a real number randomly generated in the continuous interval [0, 1). A decoder maps each vector of random keys to a solution of the optimization problem being solved and computes its cost. The benefit of this approach is that all genetic operators and transformations can be maintained within the unitary hypercube, regardless of the problem being addressed. This enhances the productivity and maintainability of the core framework. The algorithm starts with a population of P vectors of random keys. At each iteration, the vectors are partitioned into two sets: a smaller set of high-valued elite solutions and the remaining non-elite solutions. All elite elements are copied, without change, to the next population. A small number of random-key vectors (the mutants) is added to the population of the next iteration. The remaining elements of the population of the next iteration are generated by combining, with the parametrized uniform crossover of Spears and DeJong (1991), pairs of solutions. This chapter reviews random-key genetic algorithms and describes an effective variant called biased random-key genetic algorithms.

Spiking neural networks (SNNs) have emerged as a class of bio -inspired networks that leverage sparse, event-driven signaling to achieve low-power computation while inherently modeling temporal dynamics. Such characteristics align closely with the demands of ubiquitous computing systems, which often operate on resource-constrained devices while continuously monitoring and processing time-series sensor data. Despite their unique and promising features, SNNs have received limited attention and remain underexplored (or at least, under-adopted) within the ubiquitous computing community. To address this gap, this paper first introduces the core components of SNNs, both in terms of models and training mechanisms. It then presents a systematic survey of 76 SNN-based studies focused on time-series data analysis, categorizing them into six key application domains. For each domain, we summarize relevant works and subsequent advancements, distill core insights, and highlight key takeaways for researchers and practitioners. To facilitate hands-on experimentation, we also provide a comprehensive review of current software frameworks and neuromorphic hardware platforms, detailing their capabilities and specifications, and then offering tailored recommendations for selecting development tools based on specific application needs. Finally, we identify prevailing challenges within each application domain and propose future research directions that need be explored in ubiquitous community. Our survey highlights the transformative potential of SNNs in enabling energy-efficient ubiquitous sensing across diverse application domains, while also serving as an essential introduction for researchers looking to enter this emerging field.