Abstract
In this paper, first we derive a novel relaxation method for the system of linear inequalities and apply it to the learning for associative memories. Since the proposed intersection learning can guarantee the recall of all training data, it can greatly enlarge the storage capacity of associative memories. In addition, it requires much less weights renewal times than the conventional methods. We also propose a multimodule associative memory which can be learned by the intersection learning algorithm. The proposed associative memory can deal with many-to-many associations and it is applied to a knowledge processing task. Computer simulation results show the effectiveness of the proposed learning algorithm and associative memory.
| Original language | English |
|---|---|
| Pages | 377-386 |
| Number of pages | 10 |
| Publication status | Published - 1998 Dec 1 |
| Externally published | Yes |
| Event | Proceedings of the 1998 2nd International Conference on knowledge-Based Intelligent Electronic Systems (KES '98) - Adelaide, Aust Duration: 1998 Apr 21 → 1998 Apr 23 |
Other
| Other | Proceedings of the 1998 2nd International Conference on knowledge-Based Intelligent Electronic Systems (KES '98) |
|---|---|
| City | Adelaide, Aust |
| Period | 98/4/21 → 98/4/23 |
ASJC Scopus subject areas
- Computer Science(all)
Fingerprint Dive into the research topics of 'Neural associative memory for intelligent information processing'. Together they form a unique fingerprint.
Cite this
Hattori, M., & Hagiwara, M. (1998). Neural associative memory for intelligent information processing. 377-386. Paper presented at Proceedings of the 1998 2nd International Conference on knowledge-Based Intelligent Electronic Systems (KES '98), Adelaide, Aust, .