Use of Genetic Programming for the Search of a New Learning Rule for Neural Networks

| In previous work ((1, 2, 3]) we explained how to use standard optimization methods such as simulated annealing, gradient descent and genetic algorithms to optimize a parametric function which could be used as a learning rule for neural networks. To use these methods, we had to choose a xed number of parameters and a rigid form for the learning rule. In this article, we propose to use genetic programming to nd not only the values of rule parameters but also the optimal number of parameters and the form of the rule. Experiments on classiica-tion tasks suggest genetic programming nds better learning rules than other optimization methods. Furthermore, the best rule found with genetic programming outperformed the well-known backpropagation algorithm for a given set of tasks.