This study investigates whether feedforward neural networks with two hidden layers generalise better than those with one. In contrast to the existing literature, a method is proposed which allows these networks to be compared empirically on a hidden-node-by-hidden-node basis. This is applied to ten public domain function approximation datasets. Networks with two hidden layers were found to be better generalisers in nine of the ten cases, although the actual degree of improvement is case dependent. The proposed method can be used to rapidly determine whether it is worth considering two hidden layers for a given problem

No abstract

Two-hidden-layer feedforward neural networks are investigated for the existence of an optimal hidden node ratio. In the experiments, the heuristic = (0.5 + 1), where is the number of nodes in the first hidden layer and 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 , with very little penalty. Further reductions in search complexity to logarithmic could be possible using existing methods developed by the Authors.

No abstract

No abstract