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

2019/06/01 by Khaled F. Hussain, Hussain, Khaled F., Mohamed Yousef Bassyouni +3
Computer Science · Engineering · #Advanced Memory and Neural Computing #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #G.3 #I.2 #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.1906.08864

openalex publication_date 2019/06/01 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28

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.

Citations

• A quantitative description of membrane current and its application to conduction and excitation in nerve
• The perceptron: A probabilistic model for information storage and organization in the brain.
• A Novel Connectionist System for Unconstrained Handwriting Recognition
• Sequence to Sequence Learning with Neural Networks
• Multilayer feedforward networks are universal approximators
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
• ImageNet classification with deep convolutional neural networks
• Neuromorphic electronic systems
• Simple model of spiking neurons
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Deep learning in spiking neural networks
• Question Answering with Subgraph Embeddings

Related

• Spiking Neural Networks with Random Network Architecture
• You Only Spike Once: Improving Energy-Efficient Neuromorphic Inference to ANN-Level Accuracy
• Spiking Neural Networks: The Future of Brain-Inspired Computing
• Improving classification accuracy of feedforward neural networks for spiking neuromorphic chips
• Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks