Abstract
There have been a lot of researches which apply evolutionary techniques to layered neural networks. However, their applications to Hopfield neural networks remain few so far. We are applying genetic algorithms to fully connected associative memory model of Hopfield. In an earlier paper, we reported that random weight matrices were evolved to store some number of patterns only by means of a simple genetic algorithm. In this paper we present that the storage capacity can be enlarged by incorporating Lamarckian inheritance to the genetic algorithm.
| Original language | English |
|---|---|
| Pages | 676-680 |
| Number of pages | 5 |
| Publication status | Published - Jan 1 1996 |
| Event | Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96 - Nagoya, Jpn Duration: May 20 1996 → May 22 1996 |
Other
| Other | Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96 |
|---|---|
| City | Nagoya, Jpn |
| Period | 5/20/96 → 5/22/96 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Engineering(all)
Cite this
Lamarckian evolution of associative memory. / Imada, Akira; Araki, Keijiro.
1996. 676-680 Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .Research output: Contribution to conference › Paper
}
TY - CONF
T1 - Lamarckian evolution of associative memory
AU - Imada, Akira
AU - Araki, Keijiro
PY - 1996/1/1
Y1 - 1996/1/1
N2 - There have been a lot of researches which apply evolutionary techniques to layered neural networks. However, their applications to Hopfield neural networks remain few so far. We are applying genetic algorithms to fully connected associative memory model of Hopfield. In an earlier paper, we reported that random weight matrices were evolved to store some number of patterns only by means of a simple genetic algorithm. In this paper we present that the storage capacity can be enlarged by incorporating Lamarckian inheritance to the genetic algorithm.
AB - There have been a lot of researches which apply evolutionary techniques to layered neural networks. However, their applications to Hopfield neural networks remain few so far. We are applying genetic algorithms to fully connected associative memory model of Hopfield. In an earlier paper, we reported that random weight matrices were evolved to store some number of patterns only by means of a simple genetic algorithm. In this paper we present that the storage capacity can be enlarged by incorporating Lamarckian inheritance to the genetic algorithm.
UR - http://www.scopus.com/inward/record.url?scp=0029712943&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029712943&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:0029712943
SP - 676
EP - 680
ER -