1998 Fiscal Year Final Research Report Summary
A Neural Network Model with interaction between Extraneous Information and Internal Memory
| Project/Area Number |
09650465
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
計測・制御工学
|
|---|
| Research Institution | Nagoya Institute of Technology |
|---|
Principal Investigator |
IWATA Akira Nagoya Inst.of Tech., Faculty of Engineering, Professor, 工学部, 教授 (10093098)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KUROYANAGI Susumu Nagoya Inst.of Tech., Faculty of Engineering, Research Associate, 工学部, 助手 (10283475)
MATSUO Hiroshi Nagoya Inst.of Tech., Faculty of Engineering, Associate Professor, 工学部, 助教授 (00219396)
|
|---|
| Project Period (FY) |
1997 – 1998
|
| Keywords | Newral Network / Sensor Fusion / Pattern Recognition / Hierarchical Structure / Incremental Learning / Symbolic Pattern |
|---|
| Research Abstract |
In this study, we focused on the memory system of the human being and constructed a incremental learning neural network model for the symbolic patterns. The network model has a hierarchical structure and each layer has neuron blocks which recognize local features of the lower layer's output pattern. The network model does bottom-up processing and finally recognize the input pattern as the integrated information of the local features. Each neuron block is controlled by a learning trigger signal and can learn the lower layer's patterns independently. Therefore, if there are partial differences between the input pattern and the learned patterns, the network can learn only the differences between them incrementally. In the case of dealing with multi-sense information, the network model can learn only the partial information which the network model have not learned yet. In the study, we constructed the incremental learning network model. And we showed the learning ability of the model by simulations. In the first work, we tested the model by using 26 patterns as the distributed patterns that imitated the alphabet characters. As the result of the simulation, we showed the model could do incremental learning all of the patterns and recognize them after the learning process. And then, we used 200 patterns imitated the kanji characters which had "hen" and "tsukuri" structures. Each input pattern had a combination of "hen" pattern and "tsukuri" pattern, and there were about 50 "hen" patterns and 50 "tsukuri" patterns in the 200 input patterns. As the result of the simulations, the model could learn all of 200 patterns and learn only the partial differences between the "hen" or "tsukuri" patterns. We presented the above results at the IEICE meetings of technical group NC98 (Mar.1998)
|
