Title :
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
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;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1380198
