A MACHINE LEARNING-METHOD FOR GENERATION OF A NEURAL NETWORK ARCHITECTURE - A CONTINUOUS ID3 ALGORITHM

This paper describes the relation between the decision trees generated by a machine learning algorithm and the hidden layers of a neural network. A continuous ID3 algorithm is proposed that converts decision trees into hidden layers. The algorithm allows self-generation of a feedforward neural network architecture. In addition, it allows interpretation of the knowledge embedded in the generated connections and weights. A fast simulated annealing strategy, known as Cauchy training, is incorporated into the algorithm to escape from local minima. The performance of the algorithm is analyzed on spiral data.