Structural learning in artificial neural networks using sparse optimization

In this paper, the problem of simultaneously estimating the structure and parameters of artificial neural networks withmultiple hidden layers is considered. A method based on sparse optimization is proposed. The problem is formulated as an l0-norm minimization problem, so that redundant weights are eliminated from the neural network. Such problems are in general combinatorial, and are often considered intractable. Hence, an iterative reweighting heuristic for relaxing the l0-norm is presented. Experiments have been carried out on simple benchmark problems, both for classification and regression, and on a case study for estimation of waste heat recovery in ships. All experiments demonstrate the eectiveness of the algorithm.