| Presentation | 1998/5/25 A Semantic Neural Network for Leaning by Analogy:Formation of Internal Abstraction Model and Abstraction/De-Abstraction Mappings Toshiharu Watanabe, Syozo Yasui, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A new semantic neural network is presented for learning by analogy. The paradigm assumes relational isomorphism. The analogy concept is formed as an internal abstraction model as a result of training by examples. The network also developes abstraction and de-abstraction mappings which interface between general and specific situations. Analogical inference tests were made for some examples including multiple analogies, to show the feasibility of the network. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Analogy / Semantic Network / Learning / Inference / Pruning |
| Paper # | |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 1998/5/25(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 Semantic Neural Network for Leaning by Analogy:Formation of Internal Abstraction Model and Abstraction/De-Abstraction Mappings |
| Sub Title (in English) | |
| Keyword(1) | Analogy |
| Keyword(2) | Semantic Network |
| Keyword(3) | Learning |
| Keyword(4) | Inference |
| Keyword(5) | Pruning |
| 1st Author's Name | Toshiharu Watanabe |
| 1st Author's Affiliation | Kyushu Institute of Technology() |
| 2nd Author's Name | Syozo Yasui |
| 2nd Author's Affiliation | Kyushu Institute of Technology |
| Date | 1998/5/25 |
| Paper # | |
| Volume (vol) | vol.98 |
| Number (no) | 77 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |