Thermodynamics of Learning Physical Phenomena
Elías Cueto, Francisco Chinesta
Abstract
Abstract Thermodynamics could be seen as an expression of physics at a high epistemic level. As such, its potential as an inductive bias to help machine learning procedures attain accurate and credible predictions has been recently realized in many fields. We review how thermodynamics provides helpful insights in the learning process. At the same time, we study the influence of aspects such as the scale at which a given phenomenon is to be described, the choice of relevant variables for this description or the different techniques available for the learning process.
Topics & Concepts
Process (computing)Scale (ratio)PhenomenonComputer scienceStatistical physicsMachine learningArtificial intelligencePhysicsEpistemologyPhilosophyQuantum mechanicsOperating systemMachine Learning in Materials ScienceModel Reduction and Neural NetworksProtein Structure and Dynamics