GST networks: learning emergent spatiotemporal correlations

Author

Tumuluri, Chaitanya ; Mohan, Chilukuri K. ; Choudhary, Alok N.

Author_Institution

Syracuse Univ., NY, USA

Volume

3

fYear

1996

fDate

3-6 Jun 1996

Firstpage

1652

Abstract

This paper presents two novel networks-the growing cell structure instantaneous spatio-temporal (GIST) network, and growing cell structure epochal spatio-temporal (GEST) network-which combine unsupervised feature-extraction and Hebbian learning, for tracking emergent correlations in the evolution of spatio-temporal distributions. The networks were successfully tested on the challenging data mapping problem, using an execution driven simulation of their implementation in hardware

Keywords

Hebbian learning; correlation methods; data handling; feature extraction; self-organising feature maps; unsupervised learning; GCS epochal spatiotemporal network; GCS instantaneous spatiotemporal network; GEST network; GIST network; Hebbian learning; data mapping; emergent spatiotemporal correlations; feature-extraction; growing cell structure network; mapping dynamics; unsupervised learning; Character generation; Data mining; Feature extraction; Hardware; Hebbian theory; Neurons; Production; Quantization; Spatiotemporal phenomena; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1996., IEEE International Conference on

Conference_Location

Washington, DC

Print_ISBN

0-7803-3210-5

Type

conf

DOI

10.1109/ICNN.1996.549148

Filename

549148