Presentation 2005/11/11
Time Series Analysis of Chaos Neural Network Output Randomness and Fractal Dimensions
Osamu OHIRA, Yasutaka NIHEI, Takahiro NAKANISHI, Hitoaki YOSHIDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have been reported on the chaos neural network (CNN) which consists of normal neurons and can generate chaotic outputs. In this paper, we reports time series analysis on higher bits and lower bits of fixed decimal outputs from CNN as independent time series, respectively. Result of analysis suggests that time series of the lower bits has randomness, and that of the higher bits has deterministic and fractal property.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) chaos / neural network / time series analysis / fractal / random number
Paper # NLP2005-68,NC2005-60
Date of Issue

Conference Information
Committee NC
Conference Date 2005/11/11(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Time Series Analysis of Chaos Neural Network Output Randomness and Fractal Dimensions
Sub Title (in English)
Keyword(1) chaos
Keyword(2) neural network
Keyword(3) time series analysis
Keyword(4) fractal
Keyword(5) random number
1st Author's Name Osamu OHIRA
1st Author's Affiliation Graduate School of Computer and Informaition Sciences, Iwate University()
2nd Author's Name Yasutaka NIHEI
2nd Author's Affiliation Shinko Electric Co., Ltd.
3rd Author's Name Takahiro NAKANISHI
3rd Author's Affiliation Super Computing and Information Sciences Center Iwate University
4th Author's Name Hitoaki YOSHIDA
4th Author's Affiliation Super Computing and Information Sciences Center Iwate University
Date 2005/11/11
Paper # NLP2005-68,NC2005-60
Volume (vol) vol.105
Number (no) 418
Page pp.pp.-
#Pages 6
Date of Issue