Memory Search using Genetic Algorithms and a Neural Network Model

An information processing task which generates combinatorial explosion and program complexity when it is treated by a serial algorithm is investigated using both Genetic Algorithms (GA) and a neural network model (NN). The task in question is to find a target memory from a set of stored entries in the form of "attractors" in a high dimensional state space. The representation of entries in the memory is distributed ("an auto associative neural network" in this paper), and the problem is to find an attractor under a given access information where the uniqueness or even existence of a solution is not always guaranteed ( an ill-posed problem ). The GA is used as an algorithm for generating a search orbit to search effectively for a state which satisfies the access condition and belongs to the target attractor basin in state space. The NN is used to retrieve the corresponding entry from the network. The results of our computer simulation indicate that the present method is superior to a search method which uses random walk in state space. Our technique may prove useful in the realization of flexible and adaptive information processing, since pattern search in high dimensional state spaces is common in various kinds of parallel information processing.