Abstract
In training a neural network we usually have to create a set of learning samples, which is a number of sample problem and desired output pairs. However sometimes it is difficult to provide an effective learning sample especially when the structure of the pattern space is complex. In this paper we introduce an algorithm that can actively self produce the effective sample pattern while advancing the learning process.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the International Joint Conference on Neural Networks |
| Place of Publication | Piscataway, NJ, United States |
| Publisher | Publ by IEEE |
| Pages | 2548-2551 |
| Number of pages | 4 |
| Volume | 3 |
| ISBN (Print) | 0780314212, 9780780314214 |
| Publication status | Published - 1993 |
| Event | Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn Duration: 1993 Oct 25 → 1993 Oct 29 |
Other
| Other | Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) |
|---|---|
| City | Nagoya, Jpn |
| Period | 93/10/25 → 93/10/29 |
ASJC Scopus subject areas
- Engineering(all)