Improving the Efficiency of Spiking Network Learning

Vaenthan Thiruvarudchelvan, Wayne Moore, Michael Antolovich

Research output: Book chapter/Published conference paperConference paperpeer-review

2 Citations (Scopus)
4 Downloads (Pure)


Spiking networks are third generation artificial neural networks with a higher level of biological realism. This realism comes at the cost of extra computation, which alongside their complexity makes them impractical for general machine-learning applications. We propose that for some problems, spiking networks can actually be more efficient than second generation networks. This paper presents several enhancements to the supervised learning algorithm SpikeProp, including reduced precision, fewer subconnections, a lookup table and event-driven computation. The cputime required by our new algorithm SpikeProp+ was measured and compared to multilayer perceptron backpropagation. We found SpikeProp+ to use 20 times less CPU than SpikeProp for learning a classifier, but it remains ten times slower than the perceptron network. Our new networks are not optimal however, and several avenues exist for achieving further gains. Our results suggest it may be possible to build highly-efficient neural networks in this way.
Original languageEnglish
Title of host publicationICONIP 2013
Subtitle of host publication20th Conference proceedings
EditorsMinho Lee
Place of PublicationGermany
Number of pages8
Publication statusPublished - 2013
EventInternational Conference on Neural Information Processing - Daegu, South Korea, Korea, Republic of
Duration: 03 Nov 201307 Nov 2013

Publication series

ISSN (Print)0302-9743


ConferenceInternational Conference on Neural Information Processing
Country/TerritoryKorea, Republic of


Dive into the research topics of 'Improving the Efficiency of Spiking Network Learning'. Together they form a unique fingerprint.

Cite this