Neural networks handling sequential patterns

Authors:
Taiga Yamasaki;Yoshinori Kataoka;Katsuro Kameyama;Kaoru Nakano
Affiliations:
Division of Biophysical Engineering, Department of Systems and Human Science, Graduate School of Engineering Science, Osaka University, 1-3 Machikaneyama, Toyonaka, Osaka 560-8531, Japan;Sony Digital Network Applications Inc., 6-7-35 Kitashinagawa Shinagawaku, Tokyo 141-0001, Japan;Division of Neurophysiology, Osaka University Graduate School of Medicine, Suita 565-0871, Japan;Department of Mechatronics, Tokyo University of Technology, 1404-1 Katakura-machi, Hachioji-shi, Tokyo 192-0982, Japan and Research Organization for Information Science & Technology, 2-2-54 Nakame ...
Venue:
Information Sciences—Informatics and Computer Science: An International Journal - Mining stream data
Year:
2004

Citing 1
Cited 2

Modular construction of time-delay neural networks for speech recognition

Neural Computation

Temporal analysis of clusters of supermarket customers: conventional versus interval set approach

Information Sciences—Informatics and Computer Science: An International Journal
Temporal analysis of clusters of supermarket customers: conventional versus interval set approach

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

In order to model thinking process in human brain, it is necessary to construct neural network models handling time-varying inputs. Such networks are required to be able to retain information of their past behaviors. This motivates us to introduce a concept "stimulus-accumulation-effect." In our models, each artificial neuron accumulates past stimulus effect until it is excited by the influence of current input as well as the accumulation. This effect makes it possible for the neural networks to scan (recall) all embedded memories sequentially, and to associate temporal sequences (such as melodies) with corresponding static patterns (their images and names).