- Title
- A novel hybrid neural learning algorithm using simulated annealing and quasisecant method
- Creator
- Yearwood, John; Bagirov, Adil; Seifollahi, Sattar
- Date
- 2011
- Type
- Text; Conference proceedings
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/42269
- Identifier
- vital:4882
- Identifier
- http://www.scopus.com/inward/record.url?eid=2-s2.0-84870518810&partnerID=40&md5=551419f412f8ec0af682d1b93a938227
- Abstract
- In this paper, we propose a hybrid learning algorithm for the single hidden layer feedforward neural networks (SLFNs) for data classification. The proposed hybrid algorithm is a two-phase learning algorithm and is based on the quasisecant and the simulated annealing methods. First, the weights between the hidden layer and the output layer nodes (output layer weights) are adjusted by the quasisecant algorithm. Then the simulated annealing is applied for global attribute weighting. The weights between the input layer and the hidden layer nodes are fixed in advance and are not included in the learning process. The proposed two-phase learning of the network is a novel idea and is different from that of the existing ones. The numerical results on some benchmark data sets are also reported and these results are promising. © 2011, Australian Computer Society, Inc.
- Publisher
- Ballarat, VIC Australian Computer Society, Inc.
- Rights
- Copyright 2011 Australian Computer Society, Inc.
- Rights
- This metadata is freely available under a CCO license
- Subject
- Attribute weighting; Classification; Quasisecant method; Benchmark data; Data classification; Hidden layer nodes; Hidden layers; Hybrid algorithms; Hybrid learning algorithm; Input layers; Numerical results; Output layer; Simulated annealing method; Single-hidden layer feedforward neural networks; Classification (of information); Feedforward neural networks; Information technology; Learning algorithms; Simulated annealing
- Hits: 5917
- Visitors: 5851
- Downloads: 1
| Thumbnail | File | Description | Size | Format |
|---|