Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity

Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity

Spike timing dependent plasticity (STDP) is a learning rule that modifies synaptic strength as a function of the relative timing of pre- and postsynaptic spikes. When a neuron is repeatedly presented with similar inputs, STDP is known to have the effect of concentrating high synaptic weights on affe...

Full description

Bibliographic Details
Main Authors: Masquelier, Timothée, Thorpe, Simon J
Format: Online
Language:English
Published: Public Library of Science 2007
Online Access:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1797822/
id pubmed-1797822
recordtype oai_dc
spelling pubmed-17978222007-02-16 Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity Masquelier, Timothée Thorpe, Simon J Research Article Spike timing dependent plasticity (STDP) is a learning rule that modifies synaptic strength as a function of the relative timing of pre- and postsynaptic spikes. When a neuron is repeatedly presented with similar inputs, STDP is known to have the effect of concentrating high synaptic weights on afferents that systematically fire early, while postsynaptic spike latencies decrease. Here we use this learning rule in an asynchronous feedforward spiking neural network that mimics the ventral visual pathway and shows that when the network is presented with natural images, selectivity to intermediate-complexity visual features emerges. Those features, which correspond to prototypical patterns that are both salient and consistently present in the images, are highly informative and enable robust object recognition, as demonstrated on various classification tasks. Taken together, these results show that temporal codes may be a key to understanding the phenomenal processing speed achieved by the visual system and that STDP can lead to fast and selective responses. Public Library of Science 2007-02 2007-02-16 /pmc/articles/PMC1797822/ /pubmed/17305422 http://dx.doi.org/10.1371/journal.pcbi.0030031 Text en © 2007 Masquelier and Thorpe. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
repository_type Open Access Journal
institution_category Foreign Institution
institution US National Center for Biotechnology Information
building NCBI PubMed
collection Online Access
language English
format Online
author Masquelier, Timothée
Thorpe, Simon J
spellingShingle Masquelier, Timothée
Thorpe, Simon J
Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity
author_facet Masquelier, Timothée
Thorpe, Simon J
author_sort Masquelier, Timothée
title Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity
title_short Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity
title_full Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity
title_fullStr Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity
title_full_unstemmed Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity
title_sort unsupervised learning of visual features through spike timing dependent plasticity
description Spike timing dependent plasticity (STDP) is a learning rule that modifies synaptic strength as a function of the relative timing of pre- and postsynaptic spikes. When a neuron is repeatedly presented with similar inputs, STDP is known to have the effect of concentrating high synaptic weights on afferents that systematically fire early, while postsynaptic spike latencies decrease. Here we use this learning rule in an asynchronous feedforward spiking neural network that mimics the ventral visual pathway and shows that when the network is presented with natural images, selectivity to intermediate-complexity visual features emerges. Those features, which correspond to prototypical patterns that are both salient and consistently present in the images, are highly informative and enable robust object recognition, as demonstrated on various classification tasks. Taken together, these results show that temporal codes may be a key to understanding the phenomenal processing speed achieved by the visual system and that STDP can lead to fast and selective responses.
publisher Public Library of Science
publishDate 2007
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1797822/
_version_ 1611394317514964992

Similar Items