Neural and Evolutionary Computing Papers

ALT Barrier coverage is a key paradigm for intrusion detection and surveillance in IoT-enabled heterogeneous wireless sensor networks, where monitoring quality depends not only on the existence of sensing barriers but also on the detectability of feasible crossing paths. In this paper, we study the obstacle-aware maximal exposure path planning problem in heterogeneous sensor fields under truncated omni-directional sensing and line-of-sight occlusion. Unlike conventional maximal exposure formulations that focus only on exposure maximization, the considered problem seeks side-to-side feasible paths that simultaneously maximize accumulated sensing exposure and minimize path length in obstacle-constrained environments. To address this bi-objective problem, we develop OG-MOEA/D, a problem-specific MOEAD method that combines a fixed-grid path representation with obstacle-aware feasibility checking and adaptive repair. The standard decomposition, neighborhood update, SBX, and polynomial mutation

ALT Reservoir computing offers a way to study the brain's wiring before it is even trained. The recurrent network remains fixed, while only a linear readout is trained. The human connectome is found to perform better than randomly rewired versions of itself, suggesting that biological wiring is special. To understand the source of this advantage, a mathematical graph-theoretic decomposition is introduced. Rewiring a weighted network changes both the regions that are connected and the weights assigned to those connections. The observed advantage therefore combines an effect of wiring with an effect of weight placement. These effects are separated by averaging the wiring term over the null model's weight rule, as a single draw introduces about one z-unit of noise. Adult and infant connectomes are then considered separately. In adult Human Connectome Project graphs, weight placement explains most of the reported effect, leaving a small but consistent wiring effect. Across the full dHCP releas

ALT This work investigates device-informed spike-timing-dependent plasticity (STDP) in spiking neural networks using a literature-derived threshold-memristor model. Local STDP commands determine programming polarity and a programming coordinate for state-dependent conductance updates in the first fully connected layer, while a backpropagation-trained readout performs classification. HSPICE simulations characterize thresholded, polarity- and state-dependent device dynamics and differential crossbar multiply-accumulate behavior. Experiments on MNIST and Fashion-MNIST compare the hybrid learning rule with direct clipped STDP and evaluate programming asymmetry, device-parameter variation, write noise, stuck-at faults, and input corruption. The hybrid model achieved 95.15% accuracy on MNIST and 85.92% on Fashion-MNIST. In a separate seed-matched comparison, it reached 95.02% and 84.79%, versus 92.33% and 83.25% for direct clipped STDP. Potentiation-dominant asymmetry reduced input-dependent fea

ALT Energy-constrained aerial platforms require accurate object detection under strict power and latency budgets, yet conventional inference remains bottlenecked by multiply-accumulate (MAC) operations. While spiking neural networks (SNNs) offer bio-inspired efficiency, many SNN detectors retain hybrid MACs in intermediate layers, or use spike-driven inference where multi-level spikes are interpreted as repeated binary events. We propose SpikeAD, a direct-trained spike-controlled neuromorphic aerial detector. In SpikeAD, sparse bounded integer spikes act strictly as multiplexer control signals for multiplier-free shift-add inference, preserving spike boundaries throughout a four-scale bidirectional feature pyramid. We introduce the Spike-Gated Multi-Scale (SGMS) block, performing receptive field expansion with activity-driven channel selection, implementable with adders and comparators. Evaluated on VisDrone and DOTA and across Nano, Small, and Medium variants, SpikeAD achieves up to 46.2%

ALT Gating mechanisms allow a fixed neural network to adapt its computation to the current input by dynamically modulating its effective parameters. In the brain, neuromodulation uses this principle to move neural circuits between dynamical regimes, and deep learning exploits input-dependent gating, e.g., in gated recurrent networks and self-attention. Input-dependent modulation has also recently been shown to improve spiking neural networks, with particularly strong benefits in small, parameter-limited ones. This makes neuromodulation especially promising for neuromorphic processors at the edge, where area, memory and energy budgets constrain network size, while circuit physics limits parameter precision. Here we demonstrate input-dependent, within-trial neuromodulation of a spiking recurrent neural network on a mixed-signal neuromorphic processor. An off-chip modulator reads the on-chip network's input and activity and adjusts its population-level gains while the chip's analog circuits c

ALT This paper presents a neural network model for storing and recalling color images of different sizes using the Cue BallRecall Net systems [1,2,3,4,5]. The Cue Ball system consists of a Recall Net composed of multiple memory neurons each responsible for memorizing a single, distinct memory and a large number of neurons that represent image patterns. The images used in this study [6] consist of ten images(see Appendix). The pixel values of these images were converted into digital values and used for subsequent processing. Accordingly, the Cue Ball contains ten Cue neurons, corresponding to the ten images stored in memory. The number of pixels varies among the images, and therefore, the number of Recall neurons comprising the Recall Net also varies accordingly. In this study, the number of Recall neurons was prepared between 106,134 and 360,000, depending on the number of pixels in each image. In this simulation, after the connection weights (wjip, vijp) had been learned, we have used the

ALT An evaluated candidate can improve a local search step, alter the population used by later steps, and affect a solver's final result. We distinguish these three questions using Da Gou Gun Optimization (DGO), a population optimizer designed for this study. Its JQ100 configuration evaluates an interpolation candidate during a two-sided probe. We define local budget value, population commitment effects and complete-policy performance, and give an exact example in which a locally better commitment leads to a worse continuation. Short-horizon matched comparisons favor interpolation on eligible quadratic states. Paired continuations yield mixed effect estimates, with primary group intervals spanning zero. Complete-policy comparisons favor JQ100 over the tested classical references in aggregate; a matched-start comparison has favorable means but intervals spanning parity. On 24 boxed BBOB functions, target-truncated geometric-mean error ratios favor JQ100 over the tested classical policies an

ALT The advent of large, high-density FPGAs such as the AMD Versal enables efficient hardware implementation of neuromorphic Ising machines, unlocking unprecedented performance for complex combinatorial optimizations. A critical application for this computing paradigm is dynamic powergrid optimization, specifically Distribution Network Reconfiguration (DNR), which seeks to mitigate severe resistive losses and reduce electricity costs by optimizing network switch configurations in real time. This paper presents an FPGA-based neuromorphic higher-order Ising machine for high-speed, adaptive DNR. By directly mapping DNR onto higher-order Ising interactions via a polynomial unconstrained binary optimization (PUBO) formulation, the proposed architecture requires only 179 spins for the IEEE 33-bus network, which represents a 6 times reduction compared to standard quadratic formulations. Implemented on an AMD Versal Premium VP1802 FPGA, the architecture executes parallel spin-group updates every 2

ALT Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective combinatorial optimization (MOCO). Yet most methods evolve the operators while leaving the process that discovers them fixed. This limits adaptation as new Pareto trade-offs and operator interactions change where and how the search should proceed. We introduce HEMO, which makes the AOD harness itself a self-evolving optimization target. HEMO maintains a persistent harness state and updates one module at a time, revising the logic that determines which experience to retrieve, which operators to improve, which parents to select, and how to formulate the orchestration of search steps. Downstream solution quality and runtime guide these updates, while a discounted UCB scheduler directs adaptation toward promising modules as their utility changes. A persistent memory filesystem preserves candidate outcomes and diagnostic feedba

ALT Continuous relaxations are commonly used as an encoding scheme for evolutionary multitasking optimization (EMTO), allowing heterogeneous tasks to be optimized within a unified search space. However, these continuous representations fundamentally reshape the induced fitness landscape, and their impact on optimization behavior and knowledge transfer remains underexplored. In this work, we bridge the gap by analyzing the interaction between the representation-induced fitness landscape and optimizer behavior through fitness landscape analysis. Using piano fingering estimation as a representative case of the subset selection problem, we introduce several encoding variants and investigate how their induced landscapes influence search dynamics and solution quality under EMTO. Our analysis indicates that transfer efficacy is strongly associated with changes in representation-induced landscape characteristics, rather than algorithmic factors alone, highlighting the representation design as the

ALT Spiking neural networks (SNNs) promise event-driven, low-power inference, but on vision tasks they still acquire rotation invariance only through data augmentation. Group-equivariant CNNs build such symmetries into the architecture, yet a faithful spiking analogue is missing: a leaky integrate-and-fire (LIF) neuron placed after a G-equivariant convolution can break equivariance through its membrane recurrence. We give a necessary and sufficient condition for this not to happen. The layer is equivariant at every time step if and only if the neuron parameters (β, vₜₕ) are constant along the joint orbits of the group action on the (group, space) index. We solve it in closed form, and it covers any elementwise stateful neuron. Its sufficiency half specialises a known result for equivariant recurrent networks; its necessity half rules out the heterogeneous per-neuron parameters common in SNNs. The per-channel parameterisation that satisfies it, Group-Coupled LIF (GC-LIF), is combined with p

ALT Synapse-resolution fruit-fly (Drosophila) connectomes enable neuron-by-neuron simulation of entire insect nervous systems, yet whole-brain models still require computationally demanding software or multiple neuromorphic chips, and single FPGAs support only small or statistical networks. Scaling to the full connectome, per-synapse spike expansion scales queue traffic with fan-out up to 11.2k, while 41-bit neuron states require 6.83 Mbit, exceeding the 6.27 Mbit on-chip block static RAM (BSRAM) of the target device. FPGAFly runs the 166.7k-neuron, 25.6M-connection leaky integrate-and-fire male central nervous system (CNS) connectome on one FPGA. Order-preserving deferred expansion queues one 64-bit descriptor per spike in source-ID order, cutting external memory traffic by 54.5%-57.9% and peak queue data by 95.6%-96.5% with bit-identical results. A 24-bit encoding shares codewords across normal, refractory, and quantized out-of-range states, reducing BSRAM usage from 438 to 270 with 1245

ALT Many real-world optimization tasks are governed not only by what should be optimized, but also by what is allowed: a solution must first satisfy physical, operational, safety, budgetary, or structural requirements before its objective value becomes meaningful. Yet benchmark design for constrained continuous optimization often treats these restrictions as fixed properties of predefined test instances. Existing generators and benchmark suites provide essential foundations for reproducible comparison, but they either focus primarily on configurable objective landscapes or expose constraint properties within limited, predefined regimes, making it difficult to ask targeted questions about constraint-induced difficulty: whether an optimizer struggles because feasible regions are small, boundaries are restrictive, variables are tightly coupled, or constraint information is poorly scaled. We introduce GNBG-C, a Generalized Numerical Benchmark Generator for Constrained Continuous Optimization.

ALT Spiking neural networks (SNNs) encode information not only in whether neurons fire but also in when they fire, and this temporal dimension shapes what a trained network reveals about its training data. Biologically inspired firing patterns can reduce membership leakage in SNNs without changing the network architecture, which positions temporal dynamics as a design variable for privacy. A change in firing behavior, however, alters stochasticity, spike timing, neuronal response, and the learning problem at once, so harnessing this effect requires identifying which of these properties produces it. This study traces that origin by separating temporal representation, stochasticity, intrinsic neuron dynamics, and learning within a common experimental framework, evaluated under a black-box membership inference attack across image and tabular benchmarks. Varying the temporal representation shows that burst-like firing patterns reduce leakage relative to regular spiking, but at a cost in accura

ALT Neural architecture search (NAS) is challenging because of the vast, non-linear space of artificial neural network (ANN) topologies. Evolutionary methods can generate architectures, but their effectiveness is limited by difficulties in preserving functional organization during mutation and recombination. Naturally evolved biological networks may provide organizational principles that support adaptation and evolvability. Here, we introduce TRON (TRansfer Of Natural networks), a neuroevolution framework that uses experimentally characterized protein-protein interaction (PPI) networks as architectural priors. Instead of starting from random topologies, TRON reuses biological interaction patterns as structural building blocks. It combines classical evolutionary operators with neuroevolution-inspired mechanisms, including speciation, and introduces species quarantine to protect newly generated architectures during early maturation. We evaluated TRON against established evolutionary and neur

ALT Many decision-making tasks are inherently multi-objective. Interactive evolutionary multi-objective optimization algorithms (iEMOAs) are particularly well-suited to help the decision-maker find their most preferred solution. However, many of these algorithms employ black-box preference models. For high-stakes decision-making tasks, like healthcare and defense, a high level of transparency is needed, for instance to support accountability. We propose an interpretable iEMOA which uses active learning to efficiently learn a tree-based preference model directly from pairwise comparisons. The survival operator of NSGA-II and NSGA-III is extended with the learned preference model to guide the algorithm towards the region of interest. An extensive experimental study compares the proposed method to a state-of-the-art black-box model and a state-of-the-art interpretable model. Results indicate that our proposed model outperforms the alternatives in terms of finding the most preferred solution a

ALT Besides domination-based algorithms such as the NSGA-II, the decomposition-based MOEA/D is one of the most popular and successful optimization heuristic for multi-objective problems. It decomposes the problem into several, single-objective subproblems. By solving these in a co-evolutionary manner and archiving non-dominated solutions, it approximates or computes the Pareto front. Interestingly, so far no advantages from the co-evolutionary communication of subproblem solutions were proven. In this first mathematical runtime analysis addressing this research question, we investigate how the mutation-based MOEA/D solves the classic OneMinMax benchmark when solutions are exchanged among subproblems in different distances r. We show, for the first time, that the MOEA/D profits from an exchange of solutions, and that already very small communication radii r are sufficient to maximally profit from this feature of the algorithm. More precisely, for all values r ≥ 1 we prove a tight runtime gu

ALT The MOEA/D is one of the most successful multi-objective evolutionary algorithms. It operates by decomposing the optimization problem into single-objective subproblems, which are then solved in a co-evolutionary manner. The performance of the MOEA/D depends critically on this decomposition. In this work, we propose a novel way to adjust this decomposition on the fly, for the case of discrete bi-objective optimization. Different from all previous works in this direction, we support our new algorithm with a proven performance guarantee. This is the first work that rigorously proves the runtime of a dynamic multi-objective evolutionary algorithm. For monotonic distortions of the simple LOTZ benchmark, it is known that classic decompositions leave large holes in the Pareto front, making it very hard for the MOEA/D to cover the entire Pareto front. In contrast, we prove that our self-adjusting MOEA/D solves all these LOTZ problems in an expected number of O(n⁴) function evaluations. This re

ALT Reservoir computing shifts the focus from training a system's internal dynamics to designing dynamics that expose useful computational capabilities via linear projection. We study random Boolean networks as reservoirs: cellular automata with random recurrent wiring and a random rule at each node. Their main parameter is the connectivity, the mean number of edges into a node. Without input, these networks pass from ordered to chaotic dynamics at a connectivity of 2, where their dynamics are expected to facilitate computation. How the input is connected is itself a design factor: if the input shares the network's edges, the connectivity sets both the dynamics and how many nodes receive the input, the input fan-out. We set the input fan-out separately and compare 7,560 reservoir designs, all combinations of six design factors, each built as many random reservoirs, on recalling the majority or the parity of a few input bits seen several steps earlier. The optimal connectivity falls from 2.

ALT The neighborhood topology of particle swarm optimization (PSO) determines information propagation and regulates the exploration-exploitation balance. However, existing evaluation methods based on fitness and spatial diversity fail to characterize the dynamic evolution internal interaction structure of the population. To address this gap, this paper focuses on small-scale PSO (20-50 particles) with regular topologies and models the iterative process as a dynamic weighted influence graph. We construct a multi-scale information-flow evaluation framework covering micro-, meso-, and macro-level metrics, and propose a freeze-point detection method based on effective nodes, a macro-level distributional metric. Experiments on CEC2017 benchmark functions show that the information flow structure freezes early in the search (3 percent - 22 percent for representative configurations and 15 percent-49 percent for global medians) and remains unchanged thereafter. The freeze time follows the order Gbe