eCite Digital Repository

Analysis of SpikeProp Convergence with Alternative Spike Response Functions


Thiruvarudchelvan, V and Crane, JW and Bossomaier, T, Analysis of SpikeProp Convergence with Alternative Spike Response Functions, 2013 IEEE Symposium on Foundations of Computational Intelligence (FOCI), 16-19 April 2013, Singapore ISBN 978-1-4673-5900-9 (2013) [Refereed Conference Paper]

Copyright Statement

Copyright 2013 IEEE

Official URL:


—SpikeProp is a supervised learning algorithm for spiking neural networks analogous to backpropagation. Like backpropagation, it may fail to converge for particular networks, parameters and datasets. However there are several behaviours and additional failure modes unique to SpikeProp which have not been explicitly outlined in the literature. These factors hinder the adoption of SpikeProp for general machine learning use. In this paper we examine the mathematics of SpikeProp in detail and identify the various causes of failure therein. The analysis implies that applying certain constraints on parameters like initial weights can improve the rates of convergence. It also suggests that alternative spike response functions could improve the learning rate and reduce the number of convergence failures. We tested two alternative functions and found these predictions to be true.

Item Details

Item Type:Refereed Conference Paper
Research Division:Psychology
Research Group:Biological psychology
Research Field:Behavioural neuroscience
Objective Division:Expanding Knowledge
Objective Group:Expanding knowledge
Objective Field:Expanding knowledge in psychology
UTAS Author:Crane, JW (Dr James Crane)
ID Code:127110
Year Published:2013
Deposited By:Office of the School of Medicine
Deposited On:2018-07-11
Last Modified:2018-08-06

Repository Staff Only: item control page