Formalism of Quantum Mechanics From the Point of View of Machine Learning [in Russian]

Slides: Speaker: Alexander Lobashev, Skoltech This talk will be devoted to an introduction to quantum mechanics from the point of view of machine learning. We briefly review the main ideas of classical mechanics and related concepts from Hamiltonian Monte Carlo methods: the Hamilton’s equations and the principle of least action. After that, we introduce stochasticity into the Hamilton equations and, using the Fokker-Planck equation for the probability distribution function, we arrive at the Schrödinger equation. After introducing the basic axioms of quantum mechanics, we will discuss its main features, such as the noncommutativity of observables, the uncertainty principle, and entanglement. Finally, we will review the path integral formulation of quantum mechanics and see some analogies between the approximation of path integrals and ensemble methods in deep learning.