Machine Learning for Identification of Quantum Effects in Dirac-Lorentz Electrodynamics

Abstract

A computational methodology based at Machine Learning in order to identify quantum effects at Dirac-Lorentz electrodynamics, is proposed. Essentially, the present contribution is based in an algorithm that employs the Mitchell’s criteria based at (i) task, (ii) performance and (iii) experience. Thus, the solution of covariant Dirac-Lorentz equation is done, and its interpretation is given in terms of quantum mechanics effects. The role of Machine Learning seems to be beyond the computational character and it might be perceived as an alternative way to study physics equations independently of classical or quantum territory. Simulations are presented as well as discussed.