Presentation 2013-09-27
A parameter learning method for Piecewise-Constant Chaos Oscillator with spike trains of desired ISI
Tatsuro FURUSAWA, Tadashi TSUBONE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we consider a parameter identification method for piecewise-constant chaos oscillator (PWCCO) which can generate desired spike trains by machine learning. The oscillator can generate various spike trains in response to change its parameters. In this report, we give periodic spike trains to PWCCO as the teacher signal and apply the steepest descent method to identify parameters of PWCCO which can generate spike trains with the period same as the teacher signal. We demonstrate the effectiveness of our method in numerical simulation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Machine learning / Piecewise-constant chaos oscillator / Steepest descent method / Inter-Spike-Interval
Paper # CAS2013-47,NLP2013-59
Date of Issue

Conference Information
Committee NLP
Conference Date 2013/9/19(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) A parameter learning method for Piecewise-Constant Chaos Oscillator with spike trains of desired ISI
Sub Title (in English)
Keyword(1) Machine learning
Keyword(2) Piecewise-constant chaos oscillator
Keyword(3) Steepest descent method
Keyword(4) Inter-Spike-Interval
1st Author's Name Tatsuro FURUSAWA
1st Author's Affiliation Nagaoka University of Technology()
2nd Author's Name Tadashi TSUBONE
2nd Author's Affiliation Nagaoka University of Technology
Date 2013-09-27
Paper # CAS2013-47,NLP2013-59
Volume (vol) vol.113
Number (no) 225
Page pp.pp.-
#Pages 4
Date of Issue