Genetic Algorithms and its use with back-propagation network
This work addresses training efficiency for neural network practitioners, but it appears incremental as it extends existing genetic algorithm techniques.
The paper tackles the problem of training set generation and selection for back-propagation networks by proposing a novel method using genetic algorithms, resulting in improved efficiency in finding suitable solutions.
Genetic algorithms are considered as one of the most efficient search techniques. Although they do not offer an optimal solution, their ability to reach a suitable solution in considerably short time gives them their respectable role in many AI techniques. This work introduces genetic algorithms and describes their characteristics. Then a novel method using genetic algorithm in best training set generation and selection for a back-propagation network is proposed. This work also offers a new extension to the original genetic algorithms