In this paper, we address the problem of automating the design of artificial neural networks based on a gradient descent learning algorithm for solving a given application. There are many possible network configurations for solving the given application, and enumerating and training all of them is impossible in any reasonable amount of time. We present a heuristic design method for selecting and training promising neural networks, with the goal of maximizing a given objective function of cost and training time and satisfying given resource constraints, Our proposed method consists of two parts. For a given amount of time divided into quanta, the first part of our method systematically selects promising network configurations and trains them for various quanta of time. Unpromising configurations are pruned as the search proceeds. The second part of our method refines the error measure used in the first part. When the time limit is exceeded, a set of promising but possibly partially trained networks are reported. We have applied the method to a variety of benchmark problems and found it to be effective in identifying promising network configurations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.