Fast backpropagation for supervised learning

In this paper, fast backpropagation (Fbp), a new, simple and computationally efficient variant of the standard backpropagation, is proposed. It continuously adapts the learning rate parameter ε, for individual synapses, using only network variables, without any significant increase in circuit complexity. The method is related to Fermi-Dirac distribution which is based upon quantum principles. The ´mean´ update procedure employed offers a fascinating degree of stability and robustness. Even on individual runs Fbp, on average, converges quicker, particularly for non-Boolean inputs, and generalizes better than Quickprop with an identical set of initial random weights.