Time series prediction using chaotic neural networks: case study of IJCNN CATS benchmark test

Author

Kozma, Robert ; Beliaev, Igor

Author_Institution

Dept. of Math. Sci., Memphis Univ., TN, USA

Volume

2

fYear

2004

fDate

25-29 July 2004

Firstpage

1609

Abstract

KIII is a strongly biologically inspired neural network model. It has a multi-layer architecture with excitatory and inhibitory neurons, which have massive lateral, feedforward, and delayed feedback connections between layers. KIII has been shown previously to be an efficient tool of classification and pattern recognition. In this work, we develop a methodology to use KIII for multi-step time series prediction. The method is applied for the IJCNN CATS benchmark data.

Keywords

chaos; feedback; feedforward neural nets; multilayer perceptrons; pattern classification; time series; IJCNN CATS benchmark test; KIII model; biologically inspired neural network model; chaotic neural networks; competition on artificial time series; delayed feedback; excitatory neurons; feedforward connections; inhibitory neurons; multilayer architecture; multistep time series prediction; pattern classification; pattern recognition; Artificial neural networks; Benchmark testing; Biological neural networks; Biological system modeling; Biology computing; Cats; Chaos; Computer aided software engineering; Mathematical model; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-8359-1

Type

conf

DOI

10.1109/IJCNN.2004.1380198

Filename

1380198