The Deterministic Evolutionary LearningAlgorithm
Rua‐Huan Tsaih · WIT transactions on information and communication technologies · 2000
Most of promising evolutionary ANNs involve a global search algorithm that is a stochastic one. We have introduced a heuristic learning algorithm for the application problems with non-binary desired outputs. The learning algorithm is named as the SBP learning algorithm, where the softening algorithm is first used to decide network's structure, and the obtained NS is then trained via BP. The design of the SBP learning algorithm does not follow the ideas of genetic inheritance and natural selection; however, during its learning process, NS develops in a deterministic way by degrees to a more advanced or mature stage. Thus the SBP learning algorithm is a deterministic evolutionary learning algorithm. The arrangement of the SBP learning algorithm is acceptable provided the ability of successfully classifying the training patterns via the softening algorithm and there are accordance between the original non-binary desired outputs and the transformed binary desired outputs.