Presentation 2005/11/12
Precisely-timed synchronization among spiking neuron circuits on silicon neural networks : Analog implementation of integrate-and-fire neurons, depressing synapses, and STDP lerning units
Tetsuya HIROSE, Alexandre SCHMID, Tetsuya ASAI, Yusuf Leblebici, Yoshihito AMEMIYA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A neural network exhibiting precisely-timed synchronization under noisy environment with depressing synapses has been proposed in the literature [4]. In this report, we construct a recurrent neural network by using silicon neuron circuits [5] and depressing synapse circuits [6] that have already been developed by the authors, and examine that timing precision among silicon neurons by numerical simulations. Consequently, timing jitter among the neurons was significantly improved by depressing synapse circuits, as compared with non-depressed one. Moreover, a simple analog STDP circuit is designed for constructing a neural network that exhibits robust synchronization under noisy environment. We confirmed its desired operations by numerical simulations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neuromophic VLSI / depressing synapse / spiking neurons / recurrent neural network / STDP
Paper # NC2005-72
Date of Issue

Conference Information
Committee NC
Conference Date 2005/11/12(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Precisely-timed synchronization among spiking neuron circuits on silicon neural networks : Analog implementation of integrate-and-fire neurons, depressing synapses, and STDP lerning units
Sub Title (in English)
Keyword(1) neuromophic VLSI
Keyword(2) depressing synapse
Keyword(3) spiking neurons
Keyword(4) recurrent neural network
Keyword(5) STDP
1st Author's Name Tetsuya HIROSE
1st Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University()
2nd Author's Name Alexandre SCHMID
2nd Author's Affiliation Microelectronic Systems Laboratory, Swiss Federal Institute of Technology(EPFL)
3rd Author's Name Tetsuya ASAI
3rd Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
4th Author's Name Yusuf Leblebici
4th Author's Affiliation Microelectronic Systems Laboratory, Swiss Federal Institute of Technology(EPFL)
5th Author's Name Yoshihito AMEMIYA
5th Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
Date 2005/11/12
Paper # NC2005-72
Volume (vol) vol.105
Number (no) 419
Page pp.pp.-
#Pages 6
Date of Issue