<?xml version="1.0" encoding="UTF-8"?> <article key="pdf/231" mdate="2008-01-20 00:00:00"> <author>Mario Gonzalez and David Dominguez and Francisco B. Rodriguez</author> <title>Learning Block Memories with Metric Networks</title> <pages>254 - 257</pages> <year>2008</year> <volume>2</volume> <number>1</number> <journal>International Journal of Computer and Information Engineering</journal> <ee>https://publications.waset.org/pdf/231</ee> <url>https://publications.waset.org/vol/13</url> <publisher>World Academy of Science, Engineering and Technology</publisher> <abstract>An attractor neural network on the smallworld topology is studied. A learning pattern is presented to the network, then a stimulus carrying local information is applied to the neurons and the retrieval of blocklike structure is investigated. A synaptic noise decreases the memory capability. The change of stability from local to global attractors is shown to depend on the longrange character of the network connectivity.</abstract> <index>Open Science Index 13, 2008</index> </article>