Presentation 2007-11-18
Development of a Vision Chip with a Switched-Resistor Network
Shosuke MORIMOTO, Seiji KAMEDA, Atsushi IWATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A neuromorphic silicon retina carries out real-time image processing by massively-parallel circuit structure. A resistive network is an important component of the silicon retina and a MOS resistor has been traditionally used as a resistive element of the network. However, the MOS resistor has high resistance but a problem of nonlinearity. In the present study, we proposed a switched-resistor network, which had high linearity, and analyzed the spatial filter characteristic. And we designed and developed a silicon retina containing the switched-resistor network and confirmed the desired responses.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) silicon retina / massively-parallel structure / resistive network / switched-resistor / Gaussian function
Paper # NC2007-55
Date of Issue

Conference Information
Committee NC
Conference Date 2007/11/11(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) Development of a Vision Chip with a Switched-Resistor Network
Sub Title (in English)
Keyword(1) silicon retina
Keyword(2) massively-parallel structure
Keyword(3) resistive network
Keyword(4) switched-resistor
Keyword(5) Gaussian function
1st Author's Name Shosuke MORIMOTO
1st Author's Affiliation Graduate School of Advanced Sciences of Matter, Hiroshima University()
2nd Author's Name Seiji KAMEDA
2nd Author's Affiliation Graduate School of Advanced Sciences of Matter, Hiroshima University
3rd Author's Name Atsushi IWATA
3rd Author's Affiliation Graduate School of Advanced Sciences of Matter, Hiroshima University
Date 2007-11-18
Paper # NC2007-55
Volume (vol) vol.107
Number (no) 328
Page pp.pp.-
#Pages 6
Date of Issue