Presentation 2006-06-16
On a fundamental learning of a Digital Spiking Neuron
Hiroyuki TORIKAI, Toshimichi SAITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The Digital Spiking Neuron (DSN) has discrete-time and discrete-state, and can generate spike-trains having various inter-spike intervals patterns. In order to develop a learning algorithm of the DSN for realizing desired characteristics of the spike-train, in this paper we study an example problem: learning of the DSN for its application to positioning and so on. First we clarify a relation between parameters of the DSN and basic properties of the spike-train theoretically. Using the theoretical result we propose a fundamental learning algorithm and analyze its basic characteristics. The analysis results suggest that the proposed algorithm can efficiently find parameters of the DSN which is suitable for the example application.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Spiking Neuron / Pulse-coupled neural network / Shift register generator / Random number generator / Cellular Automata / Ultra-discrete system / FPGA
Paper # NC2006-29
Date of Issue

Conference Information
Committee NC
Conference Date 2006/6/9(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) On a fundamental learning of a Digital Spiking Neuron
Sub Title (in English)
Keyword(1) Spiking Neuron
Keyword(2) Pulse-coupled neural network
Keyword(3) Shift register generator
Keyword(4) Random number generator
Keyword(5) Cellular Automata
Keyword(6) Ultra-discrete system
Keyword(7) FPGA
1st Author's Name Hiroyuki TORIKAI
1st Author's Affiliation EECE Dept., Hosei University()
2nd Author's Name Toshimichi SAITO
2nd Author's Affiliation EECE Dept., Hosei University
Date 2006-06-16
Paper # NC2006-29
Volume (vol) vol.106
Number (no) 102
Page pp.pp.-
#Pages 6
Date of Issue