Why dose layer-by-layer pre-training improve deep neural networks learning?

Abstract

Deep perceptron neural networks are capable of implementing a hierarchy of successive nonlinear conversions. But training these neural networks by conventional learning methods such as the error back-propagation is faced with serious obstacles owing to local minima. The layer-by-layer pre-training method has been recently proposed for training these neural networks and has shown considerable performance. In the pre-training method, the complex problem of training deep neural networks is broken down into some simple sub-problems in which some corresponding single-hidden-layer neural networks are trained through the error back-propagation algorithm. In this chapter, the theoretical principles regarding how this method effectively improves the training of deep neural networks are discussed, and the maximum discrimination theory is proposed as a proper framework for analysis of training convergence in these neural networks. Subsequently, discriminations of inputs in different layers of two similar deep neural networks, one of which is directly trained through the conventional error back-propagation algorithm and the other through layer-by-layer pre-training method, are compared, and results confirm the validity of the proposed framework.