Recognition of Spatiotemporal Patterns by Nonmonotone Neural Networks

Masahiko Morita and Satoshi Murakami

Abstract: A neural network model that recognizes spatiotemporal patterns without expanding them into spatial patterns is presented. This model forms trajectory attractors in the state space of a fully recurrent network by a simple learning algorithm using nonmonotone dynamics. When a spatiotemporal pattern is inputted after learning, the network state is attracted to the corresponding learned trajectory and the incomplete part of the input pattern is restored in the input part of the model; at the same time, the output part indicates which spatiotemporal pattern is being inputted. In addition, this model can recognize the learned patterns correctly even if they are temporally extended or contracted.

Keywords: Neural networks, Nonmonotone dynamics, Spatiotemporal pattern recognition, Trajectory attractors.


Reprint [ PDF (201KB) / gzipped PostScript (107KB) ] is available