Utilizing unique parametrization property in approximate genetic learning of feed-forward networks

A functional equivalence of feed-forward networks has been proposed to reduce the search space of learning algorithms. The description of equivalence classes has been used to introduce a unique parametrization property and consequently the so-called canonical parameterizations as representatives of functional equivalence classes. A novel genetic learning algorithm for RBF networks and perceptrons with one hidden layer that operates only on these parameterizations has been proposed. Experimental results show that our procedure outperforms the standard genetic learning. An important extension of theoretical results demonstrates that our approach is also valid in the case of approximation