Skip to main navigation Skip to search Skip to main content

Online unsupervised structural plasticity algorithm for multi-layer Winner-Take-All with binary synapses

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

This article introduces a novel hardware friendly multi-layer Winner-Take-All (WTA) architecture using neurons with nonlinear dendrites and binary synapses. The network is trained by an unsupervised spike based learning rule that modifies the network connections. Inspired by the multi-layer models of human visual cortex, the proposed architecture contains multiple layers of neurons. We show that if we increase the synaptic time constant of the layers of the system in succession, it is capable of inspecting the incoming patterns for a longer duration of time before providing a decision. After the training is complete, a unique neuron of the last layer emits a spike for same class of patterns. The results discussed in this article show that the proposed structural plasticity based WTA is capable of classifying Poisson spike trains and the two layer structure provides a 2% and a 38% increase in performance for two different tasks when sufficient neurons are employed. Moreover, compared to conventional architectures, our method is far more memory efficient for high dimensional inputs (input dimension > 200).
Original languageEnglish
Title of host publication2016 International Symposium on Integrated Circuits, ISIC 2016
PublisherIEEE
ISBN (Print)9781467390194
DOIs
Publication statusPublished - 23 Jan 2017
Externally publishedYes
Event2016 International Symposium on Integrated Circuits, ISIC 2016 - Singapore, Singapore
Duration: 12 Dec 201614 Dec 2016

Publication series

Name2016 International Symposium on Integrated Circuits, ISIC 2016

Conference

Conference2016 International Symposium on Integrated Circuits, ISIC 2016
PlaceSingapore
CitySingapore
Period12/12/1614/12/16

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Fingerprint

Dive into the research topics of 'Online unsupervised structural plasticity algorithm for multi-layer Winner-Take-All with binary synapses'. Together they form a unique fingerprint.

Cite this