Topographic independent component analysis as a model of V1 organization and receptive fields

Aapo Hyvärinen, Patrik O Hoyer
<span title="">2001</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="" style="color: black;">Neurocomputing</a> </i> &nbsp;
Independent component analysis (ICA) has been recently used as a model of natural image statistics and V1 simple cell receptive "elds. Here we show how to extend the ICA model to explain V1 topography as well. This is done by relaxing the independence assumption and ordering the basis vectors so that vectors with strong higher-order correlations are near each other. This is a new principle of topographic organization, and may be more relevant to natural image statistics than the more
more &raquo; ... l topographic ordering based on Euclidean distances. For example, our ordering leads to simultaneous emergence of complex cell properties: topographic neighborhoods act like complex cells.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="">doi:10.1016/s0925-2312(01)00490-8</a> <a target="_blank" rel="external noopener" href="">fatcat:77iuhi56mraprh6xfezhdyunwm</a> </span>
<a target="_blank" rel="noopener" href=";do=get&amp;target=Hyvarinen+and+Hoyer+sparse+coding+maps+Neurocomputing.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href=""> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> </button> </a>