Presentation 1994/12/16
A construction of neural-net-based AI systems
Manabu Kawata, Tadashi Ae,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We discuss how to construct a Neural-net-based AI System(NAI). One of solutions to acquire the knowledge for a database is to use a neural network.We specify the neural network to be a Winner-Take- All type,whose knowledge is localized to a single neuron such as in Kohonen Network.This is an advantage to an MLP neural network, and we propose an unsupervised learning method for knowledge representation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Knowledge representation / Knowledge acquisition / Neural network / LVQ / interaction / AI
Paper # NC94-59
Date of Issue

Conference Information
Committee NC
Conference Date 1994/12/16(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) A construction of neural-net-based AI systems
Sub Title (in English)
Keyword(1) Knowledge representation
Keyword(2) Knowledge acquisition
Keyword(3) Neural network
Keyword(4) LVQ
Keyword(5) interaction
Keyword(6) AI
1st Author's Name Manabu Kawata
1st Author's Affiliation Faculty of Engineering,Hiroshima University()
2nd Author's Name Tadashi Ae
2nd Author's Affiliation Faculty of Engineering,Hiroshima University
Date 1994/12/16
Paper # NC94-59
Volume (vol) vol.94
Number (no) 417
Page pp.pp.-
#Pages 8
Date of Issue