Yepes Barrera, F. Eigen Artificial Neural Networks. Preprints2019, 2019060175
Yepes Barrera, F. (2019). Eigen Artificial Neural Networks. Preprints. https://doi.org/
Yepes Barrera, F. 2019 "Eigen Artificial Neural Networks" Preprints. https://doi.org/
This work has its origin in intuitive physical and statistical considerations. The problem of optimizing 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 sys-tem is justiﬁed with an eigenvalue equation that is a variant of the Schr˜odinger 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 potential work produced by the force ﬁeld to bring a network from an arbitrary probability distribution to the potential-constrained system, which allows to establish a measure of the complexity of the system. At the end of the discussion we expose a recursive procedure that allows to reﬁne the state function and bypass some initial assumptions, as well as a discussion of some topics in quantum mechanics applied to the formalism, such as the uncertainty principle and the temporal evolution of the system. Results demonstrate how the minimization of energy eﬀectively leads to a decrease in the average error between network predictions and targets.
aritificial neural networks optimization; variational techniques; Minimum Mutual Information Principle; wave mechanics; eigenvalue problem
Computer Science and Mathematics, Computer Science
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.