Presentation | 2012-03-27 An Analysis on Ideal Searching Dynamics Realized by Lebesgue Spectrum Filter Using Associative Memory Neural Networks Kenji FUSHIKI, Tomohiro KATO, Mikio HASEGAWA, Kazuyuki AIHARA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Effectiveness of the chaotic dynamics for combinatorial optimization problems has been shown by many researches. The chaotic sequences with negative autocorrelation improve the performance of asynchronous searching methods in a chaotic noise method. Theoretical researches on chaotic CDMA have shown that such chaotic sequences with negative autocorrelation minimize the cross-correlation among the sequences. Therefore, it has been considered that such a low cross-correlation dynamics makes asynchronous searching algorithms to have ideally complicated search, which expands the searching region in a solution space, and improves the performance of the algorithms. In this paper, we analyze the expansion of the searching region on the negative autocorrelation dynamics, using associative memory neural networks. We apply the Lebesgue Spectrum Filter (LSF) to generate negative autocorrelation dynamics in the associative memory neural networks. By the computer simulation, we show that retrieve rate of the embedded pattern is improved and the searching region can be expanded by the LSF. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Combinatorial Optimization Problems / Chaos / Associative Memory / Neural Networks / Lebesgue Spectrum Filter |
Paper # | NLP2011-147 |
Date of Issue |
Conference Information | |
Committee | NLP |
---|---|
Conference Date | 2012/3/20(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) | An Analysis on Ideal Searching Dynamics Realized by Lebesgue Spectrum Filter Using Associative Memory Neural Networks |
Sub Title (in English) | |
Keyword(1) | Combinatorial Optimization Problems |
Keyword(2) | Chaos |
Keyword(3) | Associative Memory |
Keyword(4) | Neural Networks |
Keyword(5) | Lebesgue Spectrum Filter |
1st Author's Name | Kenji FUSHIKI |
1st Author's Affiliation | Department of Electrical Engineering, Faculty of Engineering, Tokyo University of Science() |
2nd Author's Name | Tomohiro KATO |
2nd Author's Affiliation | Department of Electrical Engineering, Faculty of Engineering, Tokyo University of Science |
3rd Author's Name | Mikio HASEGAWA |
3rd Author's Affiliation | Department of Electrical Engineering, Faculty of Engineering, Tokyo University of Science |
4th Author's Name | Kazuyuki AIHARA |
4th Author's Affiliation | Institute of Industrial Science, University of Tokyo |
Date | 2012-03-27 |
Paper # | NLP2011-147 |
Volume (vol) | vol.111 |
Number (no) | 498 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |