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

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 classi...

Full description

Saved in:

Bibliographic Details
Published in:	Neural networks Vol. 103; pp. 118 - 127
Main Authors:	Kulkarni, Shruti R., Rajendran, Bipin
Format:	Journal Article
Language:	English
Published:	United States Elsevier Ltd 01.07.2018
Subjects:	Algorithms Approximate computing Databases, Factual - trends Handwriting Humans Learning Memory Neural networks Neural Networks (Computer) Neuromorphic computing Neurons Pattern recognition Pattern Recognition, Automated - methods Pattern Recognition, Automated - trends Spiking neurons Supervised learning Supervised Machine Learning - trends Spiking neurons Pattern recognition Neural networks Supervised learning Approximate computing Neuromorphic computing
ISSN:	0893-6080, 1879-2782, 1879-2782
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!