Presentation 1999/3/19
A Neural Network for Four-term Analogy based on Area Representation
Kenji MIZOGUCHI, Masafumi HAGIWARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, we propose a neural network for four-term analogy based on area representation. It can deal with four-term analogy such as"teacher:student=doctor:?". The proposed network has three map layers and an input layer. In the network, area representation method based on Kohonen Feature Map is employed in order to represent knowledge, so that similar concepts are mapped in nearer area in the map layer. The proposed mechanism in the map layer can realize the movement of the excited area to the near area. we carried out the computer simulation and confirmed the followings: (1)similar concepts are mapped in the nearer area in the map layer; (2)the excited area moves among simliar concepts; (3)the proposed network realizes four-term analogy and (4)the network is robust for the lack of connections.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) area representation / four-term analogy / Kohonen self-organizing feature map
Paper # NC98-159
Date of Issue

Conference Information
Committee NC
Conference Date 1999/3/19(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 Neural Network for Four-term Analogy based on Area Representation
Sub Title (in English)
Keyword(1) area representation
Keyword(2) four-term analogy
Keyword(3) Kohonen self-organizing feature map
1st Author's Name Kenji MIZOGUCHI
1st Author's Affiliation Department of Electrical Engineering, Faculty of Science and Technology, Keio University()
2nd Author's Name Masafumi HAGIWARA
2nd Author's Affiliation Department of Electrical Engineering, Faculty of Science and Technology, Keio University
Date 1999/3/19
Paper # NC98-159
Volume (vol) vol.98
Number (no) 674
Page pp.pp.-
#Pages 8
Date of Issue