Presentation 2000/3/15
Holographic Neural Network with Optical Weighted Sum Computation by 2D Gratings
Masanori ISHIHARA, Itsuo KUMAZAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, holographic memory techniques Which represent and store a large amount of contents by laser wave interference are widely investigated. We propose a neural network which is based on the usual neural network by the wave interference and uses 2D matrix-shaped gratings for weight representation and weighted sum computation by applying the principal of holographic memory. The matrix-shaped gratings can be designed to obtain diverse weight distribution. The computation ability and the tolerance to noises of the proposed method are evaluated by some experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / weight / hlography / grating / wave interference
Paper # NC99-152
Date of Issue

Conference Information
Committee NC
Conference Date 2000/3/15(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) Holographic Neural Network with Optical Weighted Sum Computation by 2D Gratings
Sub Title (in English)
Keyword(1) neural network
Keyword(2) weight
Keyword(3) hlography
Keyword(4) grating
Keyword(5) wave interference
1st Author's Name Masanori ISHIHARA
1st Author's Affiliation Department of Computer Science Graduate School of Information Science and Engineering Tokyo Institute of Technology()
2nd Author's Name Itsuo KUMAZAWA
2nd Author's Affiliation Department of Computer Science Graduate School of Information Science and Engineering Tokyo Institute of Technology
Date 2000/3/15
Paper # NC99-152
Volume (vol) vol.99
Number (no) 686
Page pp.pp.-
#Pages 8
Date of Issue