File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Optimizing neural network weights using genetic algorithms: A case study
Title | Optimizing neural network weights using genetic algorithms: A case study |
---|---|
Authors | |
Issue Date | 1995 |
Citation | Ieee International Conference On Neural Networks - Conference Proceedings, 1995, v. 3, p. 1384-1388 How to Cite? |
Abstract | It has been demonstrated that genetic algorithms (GAs) can help search the global (or near global) optimum weights for neural networks of relatively small sizes. For larger networks, classical genetic algorithms cannot work effectively any more as too many parameters have to be optimized simultaneously. However, in this paper, it is shown that the combination of the techniques of hidden node redundancy elimination, hidden layer redundancy elimination and the use of adaptive probabilities of crossover and mutation can be used to find a satisfactory solution. |
Persistent Identifier | http://hdl.handle.net/10722/158906 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, KW | en_US |
dc.contributor.author | Lam, HN | en_US |
dc.date.accessioned | 2012-08-08T09:04:30Z | - |
dc.date.available | 2012-08-08T09:04:30Z | - |
dc.date.issued | 1995 | en_US |
dc.identifier.citation | Ieee International Conference On Neural Networks - Conference Proceedings, 1995, v. 3, p. 1384-1388 | en_US |
dc.identifier.uri | http://hdl.handle.net/10722/158906 | - |
dc.description.abstract | It has been demonstrated that genetic algorithms (GAs) can help search the global (or near global) optimum weights for neural networks of relatively small sizes. For larger networks, classical genetic algorithms cannot work effectively any more as too many parameters have to be optimized simultaneously. However, in this paper, it is shown that the combination of the techniques of hidden node redundancy elimination, hidden layer redundancy elimination and the use of adaptive probabilities of crossover and mutation can be used to find a satisfactory solution. | en_US |
dc.language | eng | en_US |
dc.relation.ispartof | IEEE International Conference on Neural Networks - Conference Proceedings | en_US |
dc.title | Optimizing neural network weights using genetic algorithms: A case study | en_US |
dc.type | Conference_Paper | en_US |
dc.identifier.email | Lam, HN:hremlhn@hkucc.hku.hk | en_US |
dc.identifier.authority | Lam, HN=rp00132 | en_US |
dc.description.nature | link_to_subscribed_fulltext | en_US |
dc.identifier.scopus | eid_2-s2.0-0029487526 | en_US |
dc.identifier.volume | 3 | en_US |
dc.identifier.spage | 1384 | en_US |
dc.identifier.epage | 1388 | en_US |
dc.identifier.scopusauthorid | Lee, KW=7501516721 | en_US |
dc.identifier.scopusauthorid | Lam, HN=7202774923 | en_US |