Accelerated optimal topology search for two-hidden-layer feedforward neural networks

Abstract

Two-hidden-layer feedforward neural networks are investigated for the existence of an optimal hidden node ratio. In the experiments, the heuristic n1 = int(0.5nh +1), where n1 is the number of nodes in the first hidden layer and nh is the total number of hidden nodes, found networks with generalisation errors, on average, just 0.023%–0.056% greater than those found by exhaustive search. This reduced the complexity of an exhaustive search from quadratic, to linear in nh, with very little penalty. Further reductions in search complexity to logarithmic could be possible using existing methods developed by the Authors.