Title :
Automatic learning in chaotic neural network
Author :
Watanabe, M. ; Aihara, K. ; Kondo, S.
Author_Institution :
Tokyo Univ., Japan
Abstract :
A learning rule which can automatically detect and learn an unknown pattern is proposed for a mutually connected neural network. We applied it to chaotic neural networks composed of neuron models with spatio-temporal inputs and refractoriness, and numerically analyzed the properties of the automatic learning.<>
Keywords :
chaos; neural nets; pattern recognition; unsupervised learning; automatic learning; chaotic neural network; mutually connected neural network; neuron models; pattern recognition; refractoriness; spatio-temporal inputs; unsupervised learning; Artificial neural networks; Biological system modeling; Chaos; Covariance matrix; Electroencephalography; Intelligent networks; Mathematical model; Neural networks; Neurons; Unsupervised learning;
Conference_Titel :
Emerging Technologies and Factory Automation, 1994. ETFA '94., IEEE Symposium on
Conference_Location :
Tokyo, Japan
Print_ISBN :
0-7803-2114-6
DOI :
10.1109/ETFA.1994.402038
