论文信息 - A Fractal Selforganizing Map with Partially Chaotic Neurons

A Fractal Selforganizing Map with Partially Chaotic Neurons

A new type of a chaotic neuron is proposed which allows a new, simplified architecture of selforganizing maps. The chaotic neurons are examined with respect to their application in selforganizing maps. A new concept of self-organizing maps with fractal architecture is proposed and its suitability for a VLSI-implementation is examined. It is shown that the efficiency of conventional selforganizing maps can be overcome while the expenditure, with regard to a hardware-realisation, is notably reduced.

Karl Goser | A. Kosak

[1] Karl Goser,et al. Hardware Design for Self-Organizing Feature Maps with Binary Input Vectors , 1993, IWANN.

[2] Jose Antonio Coarasa Perez,et al. Evidence for universal chaotic behavior of a driven nonlinear oscillator , 1982 .

[3] Teuvo Kohonen,et al. Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[4] Bernd Pompe,et al. Chaos in dissipativen Systemen , 1989 .

[5] T. Kohonen. Self-organized formation of topographically correct feature maps , 1982 .

[6] John H. Andreae,et al. A chaotic neural unit , 1993, IEEE International Conference on Neural Networks.