Training principles for unsupervised learning are often derived from motivations that appear to be independent of supervised learning. In this paper we present a simple unificatio...
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
A backpropagation learning algorithm for feedforward neural networks with an adaptive learning rate is derived. The algorithm is based upon minimising the instantaneous output erro...