Using linear initialisation to improve speed of convergence and fully-trained error in Autoencoders

Abstract

Good weight initialisation is an important step in successful training of Artificial Neural Networks. Over time a number of improvements have been proposed to this process. In this paper we introduce a novel weight initialisation technique called the Straddled Matrix Initialiser. This initialisation technique is motivated by our assumption that major, global-scale relationships in data are linear with only smaller effects requiring complex non-linearities. Combination of Straddled Matrix and ReLU activation function initialises a Neural Network as a de facto linear model, which we postulate should be a better starting point for optimisation given our assumptions. We test this by training autoencoders on three datasets using Straddled Matrix and seven other state-of-the-art weight initialisation techniques. In all our experiments the Straddeled Matrix Initialiser clearly outperforms all other methods.