Presentation | 1999/5/21 Concept Learning with Neural Networks Kanta NAKANISHI, Kazuhiko KAKEHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | There were not so many studies about neural networks dealing with concept learning, comparing with other human cognitive functions, e. g. recognition, etc. In this paper, differences in performance of concept learning between human and neural networks were studied using the same experimental subjects. One of the main performance difference in the learning was the number of the cases to be required to accomplish the learning, or neural networks required much more cases than human did. A new technique for a neural network was proposed to reduce the number of the cases required in the learning, introducing a performance of attention to the network. The validity of the technique was examined using the several examples of concept learning. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | neural networks / concept learning / attribute / attention |
Paper # | TL99-1 |
Date of Issue |
Conference Information | |
Committee | TL |
---|---|
Conference Date | 1999/5/21(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 | Thought and Language (TL) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Concept Learning with Neural Networks |
Sub Title (in English) | |
Keyword(1) | neural networks |
Keyword(2) | concept learning |
Keyword(3) | attribute |
Keyword(4) | attention |
1st Author's Name | Kanta NAKANISHI |
1st Author's Affiliation | NTT Intelligent Technology Co., Ltd.() |
2nd Author's Name | Kazuhiko KAKEHI |
2nd Author's Affiliation | Graduate School of Human Informatics, Nagoya University |
Date | 1999/5/21 |
Paper # | TL99-1 |
Volume (vol) | vol.99 |
Number (no) | 76 |
Page | pp.pp.- |
#Pages | 7 |
Date of Issue |