Computational Dynamics of Chaotic Neural Networks

tructure of a strange attractor in the phase space without getting stuck at local minima. This ability has been applied to dynamical linking of patterns stored with synaptic weights of superposed autocorrelation matrixes in associative memory networks [4] and also to dynamical searching for approximate solutions of global optima in combinatorial optimization networks [5,6]. Moreover, the model of chaotic neural networks can be extended to "transient chaotic neural This PostScript version was created from the original author's English article by the Japanese Information Sciences Project (JISP), at New York University, in collaboration with the RWCP, aiming at worldwide access to the information. Every precaution has been taken to avoid errors arising from the conversion of printed documents to electronic form, however, should there be any discrepancies, the JISP bears sole responsibility for them. Email address: www-admin@jisp.cs.nyu.edu, URL http://jisp.cs.nyu.edu/.<F3