An evolutionary approach to designing neural networks
Aviv Bergman · ACM SIGBIO Newsletter · 1992
One of the most interesting properties of neural networks is their ability to learn appropriate behavior by being trained on examples. Established learning algorithms which typically work by minimizing error through backpropagation in weight space, tend to get stuck in local optima--a tendency typical of gradient-descent methods applied to nonconvex objectives functions. Therefore, for problems of nontrivial complexity these systems must be handcrafted to a significant degree, but, the distributed nature of neural network representations make this handcrafting difficult. We are investigating an evolutionary approach to learning that will avoid this problem. This approach simulates a variable population of networks which, through processes of mutation, combination, selection, and differential reproduction, converges to a group of networks well suited to solving the task at hand. The role of the different genetic operation, e.g., recombination and mutation was also studied. We use a Connection Machine to exploit the inherent parallelism in these simulations. Population Dynamics, Evolution and Coevolution, Unsupervised learning, Adaptation, Neural Networks, Genetic Algorithm.