A model of associative memory in the brain |
| |
Authors: | Dr. Kunihiko Fukushima |
| |
Affiliation: | (1) NHK Broadcasting Science Research Laboratories, Kinuta, Setagaya, Tokyo, Japan |
| |
Abstract: | A model of associative memory for time varying spatial patterns is proposed and simulated on a digital computer. This is a network composed of many neuron-like elements, and shows an ability for associative memory similar to that of the brain.Suppose a number of sequences of spatial patterns are presented to this network, for example, 1![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) 2![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) 3![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) 4![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) 5![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) , A![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) B![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) C![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) , and so on. Then, these patterns are memorized in the network. After that, if any part of one of these sequences, say 2![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) 3 , is presented to the circuit, the rest of the sequence, 4![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) 5![rdquo](/content/r86755q6537g6r54/xxlarge8221.gif) ![rarr](/content/r86755q6537g6r54/xxlarge8594.gif) , is recalled following to it. It resembles to such a situation — if we hear a part of a melody which we have memorized in the past, the rest of the melody is recalled even after it is stopped half-way. Although the recalled patterns are not always 100% correct, they are not completely destroyed even if the presented patterns are imperfect. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|