Eigen Artificial Neural Networks
share
This work has its origin in intuitive physical and statistical considerations. An artificial neural network is treated as a physical system, composed of a conservative vector force field. The derived scalar potential is a measure of the potential energy of the network, a function of the distance between predictions and targets. Starting from some analogies with wave mechanics, the description of the system is justified with an eigenvalue equation that is a variant of the Schrodinger equation, in which the potential is defined by the mutual information between inputs and targets. The weights and parameters of the network, as well as those of the state function, are varied so as to minimize energy, using an equivalent of the variational theorem of wave mechanics. The minimum energy thus obtained implies the principle of minimum mutual information (MinMI). We also propose a definition of the work produced by the force field to bring a network from an arbitrary probability distribution to the potential-constrained system. At the end of the discussion we expose a recursive procedure that allows to refine the state function and bypass some initial assumptions. The results demonstrate how the minimization of energy effectively leads to a decrease in the average error between network and target predictions.
READ FULL TEXT