ACCURATE, ENERGY-EFFICIENT CLASSIFICATION WITH SPIKING RANDOM NEURAL NETWORK

DOI10.1017/S0269964819000147MaRDI QIDQ5070878zbMATH OpenOpenAlexWikidataFDO

Authors Khaled F. Hussain, Mohamed Yousef Bassyouni, Erol Gelenbe

Publication date 14 April 2022

Published in Probability in the Engineering and Informational Sciences (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1906.08864

zbMATH Keywords

artificial neural networkneuromorphic computingrandom neural networkspiking neural networks

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Neural nets and related approaches to inference from stochastic processes (62M45) Artificial neural networks and deep learning (68T07)

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.

Recommendations

• A network of spiking neurons for computing sparse representations in an energy-efficient way
• Solving a classification task by spiking neural network with stdp based on rate and temporal input encoding
• Minimal spiking neuron for solving multilabel classification tasks

Cites work

• 10.1162/153244303322533223
• Do we need hundreds of classifiers to solve real world classification problems?
• First draft of a report on the EDVAC
• G-networks by triggered customer movement
• G-networks with resets
• scientific article; zbMATH DE number 1330073 (Why is no real title available?)
• scientific article; zbMATH DE number 2033225 (Why is no real title available?)
• Interconnected wireless sensors with energy harvesting
• Multilayer feedforward networks are universal approximators
• Product-form queueing networks with negative and positive customers
• Queues with negative arrivals
• Stability of Product Form G-Networks

Cited in

(1)

• An FPGA implementation of deep spiking neural networks for low-power and fast classification

Describes a project that uses

Uses Software

• ImageNet
• AlexNet
• UCI
• FaceNet
• SpiNNaker

This page was built for publication: ACCURATE, ENERGY-EFFICIENT CLASSIFICATION WITH SPIKING RANDOM NEURAL NETWORK

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5070878)