Presentation 2012-04-19
Performance of Feed-Forward Neural Network with Neurogenesis
Yuta YOKOYAMA, Hironori KUMENO, Yoko UWATE, Yoshifumi NISHIO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The neurogenesis is that new neurons are generated in the human brain. It is known that the neurogenesis improves memory and thinking ability by combining new neurons with biological neural network. We consider that the neurogenesis can be applied to an artificial neural network. In this study, we adapt the neurogenesis to a Multi-Layer Perceptron (MLP). We propose the introduction method as periodic and chaotic of MLP with neurogenesis. We compare the performance of the MLP with neurogenesis to the conventional MLP for approximation of function and pattern recognition. We show the MLP with neurogenesis has better performance than the conventional MLP by computer simulations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neurogenesis / Multi-Layer Perceptron / Pattern Recognition
Paper # NLP2012-7
Date of Issue

Conference Information
Committee NLP
Conference Date 2012/4/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Performance of Feed-Forward Neural Network with Neurogenesis
Sub Title (in English)
Keyword(1) Neurogenesis
Keyword(2) Multi-Layer Perceptron
Keyword(3) Pattern Recognition
1st Author's Name Yuta YOKOYAMA
1st Author's Affiliation Department of Electrical and Electronic Engineering, Tokushima University()
2nd Author's Name Hironori KUMENO
2nd Author's Affiliation Department of Electrical and Electronic Engineering, Tokushima University
3rd Author's Name Yoko UWATE
3rd Author's Affiliation Department of Electrical and Electronic Engineering, Tokushima University
4th Author's Name Yoshifumi NISHIO
4th Author's Affiliation Department of Electrical and Electronic Engineering, Tokushima University
Date 2012-04-19
Paper # NLP2012-7
Volume (vol) vol.112
Number (no) 6
Page pp.pp.-
#Pages 5
Date of Issue