DocumentCode
1903119
Title
A chaotic neural unit
Author
Dingle, Alison A. ; Andreae, John H. ; Jones, Richard D.
Author_Institution
Dept. of Electr. & Electron. Eng., Canterbury Univ., Christchurch, New Zealand
fYear
1993
fDate
1993
Firstpage
335
Abstract
A neural unit is proposed based on a simple chaotic system. While this chaotic neural unit retains characteristics of conventional neural units, it also displays a rich range of behavior reminiscent of that observed in neurons. Networks of these neural units are shown to produce chaotic activity which is qualitatively similar to that observed in recordings of the electrical activity of the brain (EEGs). The introduction of chaotic neural units into the self-organizing map improves the ability of the network to cluster input patterns. The introduction of chaos into neural networks may enhance their performance and, at the same time, provide insights into the operation of the brain
Keywords
chaos; pattern recognition; self-organising feature maps; chaotic activity; chaotic neural unit; electrical activity; input patterns; pattern clustering; self-organizing map; Bifurcation; Biomedical engineering; Chaos; Difference equations; Displays; Electroencephalography; Hospitals; Logistics; Neurons; Physics;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1993., IEEE International Conference on
Conference_Location
San Francisco, CA
Print_ISBN
0-7803-0999-5
Type
conf
DOI
10.1109/ICNN.1993.298579
Filename
298579
Link To Document