Accurate and Energy-Efficient Classification with Spiking Random Neural Network: Corrected and Expanded Version

TL;DR

This paper introduces a spiking neural network model called the Random Neural Network (RNN) as an energy-efficient alternative to traditional artificial neural networks, demonstrating comparable classification performance on real-world datasets.

Contribution

The paper presents the RNN as a novel, practical spiking neural network classifier that matches ANN performance while offering low power consumption and high throughput.

Findings

RNN achieves comparable accuracy to ANNs on various datasets.

RNN demonstrates significant energy efficiency and high throughput.

The model is suitable for neuromorphic hardware deployment.

Abstract

Artificial Neural Network (ANN) based techniques have dominated state-of-the-art results in most problems related to computer vision, audio recognition, and natural language processing in the past few years, resulting in strong industrial adoption from all leading technology companies worldwide. One of the major obstacles that have historically delayed large scale adoption of ANNs is the huge computational and power costs associated with training and testing (deploying) them. In the mean-time, Neuromorphic Computing platforms have recently achieved remarkable performance running more bio-realistic Spiking Neural Networks at high throughput and very low power consumption making them a natural alternative to ANNs. Here, we propose using the Random Neural Network (RNN), a spiking neural network with both theoretical and practical appealing properties, as a general purpose classifier that can match the classification power of ANNs on a number of tasks while enjoying all the features of a spiking neural network. This is demonstrated on a number of real-world classification datasets.