- Title
- Connection topologies for combining genetic and least square methods for neural learning
- Creator
- Ghosh, Ranadhir
- Date
- 2004
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/54499
- Identifier
- vital:322
- Identifier
- ISSN:0334-1860
- Abstract
- In the last few years, there have been many works in the area of hybrid neural learning algorithms combining a global and local based method for training artificial neural networks. In this paper, we discuss various connection strategies that can be applied to a special kind of a hybrid neural learning algorithm group, one that combines a genetic algorithm-based method with various least square-based methods like QR factorization. The relative advantages and disadvantages of the different connection types are studied to find a suitable connection topology for combining the two different learning methods. The methodology also finds the optimum number of hidden neurons using a hierarchical combination methodology structure for weights and architecture. We have tested our proposed approach on XOR, 10 bit odd parity, and some other real-world benchmark data sets, such as the hand-writing character dataset from CEDAR, Breast cancer, and Heart Disease from the UCI machine learning repository.; C1
- Publisher
- Freund Publishing House, Ltd.
- Relation
- Journal of Intelligent Systems Vol. 13, no. 3 (2004), p. 199-232
- Rights
- Copyright Freund Publishing House, Ltd.
- Rights
- This metadata is freely available under a CCO license
- Subject
- 0801 Artificial Intelligence and Image Processing; Evolutionary learning algorithms; Learning algorithms; Neural network architecture; Computational complexity; Error analysis; Evolutionary algorithm; Genetic algorithms; Learning systems; Probability
- Reviewed
- Hits: 1339
- Visitors: 1324
- Downloads: 0