Top-down and bottom-up processing of spatiotemporal patterns in a fully recurrent network of nonmonotonic neurons

Author

Murakami, Satoshi ; Morita, Masahiko

Author_Institution

Tsukuba Univ., Ibaraki, Japan

Volume

3

fYear

1999

fDate

1999

Firstpage

1118

Abstract

A fully recurrent neural network with a nonmonotonic activation function that treats temporal sequences without expanding them into spatial patterns is described. This network associates a complex spatiotemporal pattern with a simple one using trajectory attractors formed by simple learning. Computer simulations show that the model not only has high recognition and generation abilities but can also perform advanced processing using bidirectional interactions

Keywords

learning (artificial intelligence); nonmonotonic reasoning; recurrent neural nets; spatial reasoning; temporal reasoning; bidirectional interactions; bottom-up processing; computer simulations; learning; nonmonotonic activation function; nonmonotonic neurons; recurrent neural network; spatiotemporal patterns; temporal sequences; top-down processing; trajectory attractors; Biological neural networks; Computer simulation; Delay; Intelligent networks; Neural networks; Neurons; Pattern recognition; Recurrent neural networks; Spatiotemporal phenomena; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on

Conference_Location

Perth, WA

Print_ISBN

0-7803-5871-6

Type

conf

DOI

10.1109/ICONIP.1999.844692

Filename

844692