Machine learning with quantum field theories

DOI10.22323/1.396.0201MaRDI QIDQ6377802zbMATH OpenFDO

Authors Dimitrios Bachtis, Gert Aarts, B. Lucini

Publication date 16 September 2021

Full work available at URL https://doi.org/10.22323/1.396.0201

Abstract: The precise equivalence between discretized Euclidean field theories and a certain class of probabilistic graphical models, namely the mathematical framework of Markov random fields, opens up the opportunity to investigate machine learning from the perspective of quantum field theory. In this contribution we will demonstrate, through the Hammersley-Clifford theorem, that the $ph{i}^4$ scalar field theory on a square lattice satisfies the local Markov property and can therefore be recast as a Markov random field. We will then derive from the $ph{i}^4$ theory machine learning algorithms and neural networks which can be viewed as generalizations of conventional neural network architectures. Finally, we will conclude by presenting applications based on the minimization of an asymmetric distance between the probability distribution of the $ph{i}^4$ machine learning algorithms and target probability distributions.

This page was built for publication: Machine learning with quantum field theories

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6377802)