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

TL;DR

This paper proposes using wireless sensor networks as a massively parallel, fully distributed hardware platform to implement artificial neural networks, enabling real-time solutions for large-scale complex problems.

Contribution

It introduces a novel approach to realize neural networks on wireless sensor networks, enabling real-time, large-scale, and robust neural computation in a fully distributed hardware framework.

Findings

Demonstrates the feasibility of using hundreds of thousands of sensor nodes for neural network computation.

Shows potential for real-time processing of large-scale problems.

Highlights advantages over traditional silicon- or optics-based computing.

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.