Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization

Document Type

Article

Publication Date

7-1-2018

Abstract

We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications.

Identifier

85045477348 (Scopus)

Publication Title

Neural Networks

External Full Text Location

https://doi.org/10.1016/j.neunet.2018.03.019

e-ISSN

18792782

ISSN

08936080

PubMed ID

29674234

First Page

118

Last Page

127

Volume

103

Grant

2016-SD-2717

Fund Ref

Cisco Systems

This document is currently not available here.

Share

COinS