| Presentation | 1998/5/25 A Semantic Neural Network for Leaning by Analogy:Application to Incremental Learning Hideaki Fujimura, Syozo Yasui, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This work is an extension of the preceding paper[1]in which a new semantic neur al network is described for learning by analogy. The present purpose is mainly to evaluate the network for its feasibility for incremental analogical learning. When the internal abstraction model was formed by training for a set of relation al-isomorphic analogs, data for a new analog of the same type were fed to the network. Inference tests showed that the incremental learning was fast and accurate due to exploitation of the internal abstraction model which already existed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Analogy / Semantic Network / Inference / Incremental Learning |
| 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:Application to Incremental Learning |
| Sub Title (in English) | |
| Keyword(1) | Analogy |
| Keyword(2) | Semantic Network |
| Keyword(3) | Inference |
| Keyword(4) | Incremental Learning |
| 1st Author's Name | Hideaki Fujimura |
| 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 | |