Wireless Sensor Networks as Parallel and Distributed Hardware Platform for Artificial Neural Networks

Gursel Serpen

Home/Archive/arXiv

arXiv · 2510.26492

Wireless Sensor Networks as Parallel and Distributed Hardware Platform for Artificial Neural Networks

Gursel Serpen

View original source ↗Read source document ↗Export metadata ↓

Abstract

We are proposing fully parallel and maximally distributed hardware realization of a generic neuro-computing system. More specifically, the proposal relates to the wireless sensor networks technology to serve as a massively parallel and fully distributed hardware platform to implement and realize artificial neural network (ANN) algorithms. A parallel and distributed (PDP) hardware realization of ANNs makes it possible to have real time computation of large-scale (and complex) problems in a highly robust framework. We will demonstrate how a network of hundreds of thousands of processing nodes (or motes of a wireless sensor network), which have on-board processing and wireless communication features, can be used to implement fully parallel and massively distributed computation of artificial neural network algorithms for solution of truly large-scale problems in real time. The realization of artificial neural network algorithms in a massively parallel and fully distributed hardware has been the goal of neural network computing researchers. This is because a parallel and distributed computation of artificial neural network algorithms could not have been achieved against all the advancements in silicon- or optics-based computing. Accordingly, artificial neural networks could not be applied to very large-scale problems for real time computation of solutions. This hindered the development of neural algorithms for affordable and practical solutions of challenging problems since often special-purpose computing approaches in hardware, software or hybrid (non-neural) had to be developed for and fine-tuned to specific problems that are very large-scale and highly complex. Successful implementation is likely to revolutionize computing as we know it by making it possible to solve very large scale scientific, engineering or technical problems in real time.

Explore related subjects

cs.NE cs.AR cs.DC

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Gursel Serpen. 2025-10-30. Wireless Sensor Networks as Parallel and Distributed Hardware Platform for Artificial Neural Networks. https://arxiv.org/abs/2510.26492

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution

Evolvable-Substrate HyperNEAT (ES-HyperNEAT), a bio-inspired indirect encoding that determines neuron placement and connection weights from spatial coordinates, exhibits a failure mode on MNIST as a diagnostic benchmark. Because input pixels map to a coordinate space centered at the origin, evolved networks converge on a small central cluster of input pixels, a spatial-concentration bias; prior work observed only 21% mean accuracy in this regime. Is this bias an optimization artifact or an architectural ceiling? Inspired by Mixture-of-Experts (MoE) principles, we partition the input into non-overlapping spatial segments, each assigned to a separately evolved specialist network. With 13 such experts, this design reaches 43% mean accuracy, a 106% relative improvement over the baseline. The architectural gain does not depend on data-driven aggregation: equal-weighted averaging, which uses no validation data, already yields a 70% improvement; the gain comes from partitioning, not the weighting. Receptive-field analysis shows the mechanism: partitioning forces evolution to discover features across the entire image, expanding active pixel coverage from 4% to 79%. Absolute accuracy stays below gradient-trained baselines, but the relative gain points to central bias, not the evolutionary search. Two tools are designed to generalize beyond MNIST: a receptive-field diagnostic for silent input-coverage collapse, and a spatial-partitioning remedy that restores coverage.

cs.NE↗

arXiv2026

A Bio-Plausible Visual Neural Network for Locust-Inspired Collision Perception

Locust visual systems have long served as an important biological paradigm for studying looming perception and collision avoidance. Numerous computational models have successfully reproduced the selective responses of Lobula Giant Movement Detector (LGMD) neurons to approaching objects, thereby emulating the fundamental functionality of the biological system. However, existing models remain limited in biological plausibility and robustness when operating in complex and dynamic visual environments. To address these limitations, we propose a biologically plausible neural network for locust-inspired looming detection. The proposed framework incorporates a spatially isotropic sampling strategy that mimics the ommatidial organization of the locust compound eye, a population-voting mechanism inspired by population coding in biological neural systems, and leaky integrate-and-fire neuronal dynamics to replace conventional sigmoid-based membrane activation. Systematic experiments on synthetic stimuli, laboratory sequences, and real-world driving scenarios demonstrate that the proposed model improves robustness under challenging visual conditions while preserving computational efficiency and enhancing biological fidelity. These results highlight the potential of biologically grounded neural computation for robust and efficient collision perception.

cs.NE↗

arXiv2026

Structural Fusion of Bayesian Networks with Limited Treewidth Using Genetic Algorithms

This paper introduces an evolutionary computation approach for consensus in structural Bayesian Network (BN) fusion under the constraint of limited treewidth. The consensus BN aims to reconcile multiple input BNs into a single one that retains key structural features present in the original networks. Treewidth, a graph-based parameter associated with computationally tractable inference, is utilized to restrict the complexity of the resulting network. A genetic algorithm is proposed to look for a BN that codifies as much information about the unrestricted fusion as possible while ensuring the treewidth restriction. Experimental evaluation demonstrates the genetic algorithm's ability to obtain consensus BNs with limited treewidth, providing a valuable tool for aggregating information from diverse sources while returning a computationally actionable model.

cs.NE↗