From latent dynamics to meaningful representations

arXiv:2209.00905v4 Announce Type: replace
Abstract: While representation learning has been central to the rise of machine learning and artificial intelligence, a key problem remains in making the learned representations meaningful. For this, the typical approach is to regularize the learned representation through prior probability distributions. However, such priors are usually unavailable or are ad hoc. To deal with this, recent efforts have shifted towards leveraging the insights from physical principles to guide the learning process. In this spirit, we propose …

abstract artificial artificial intelligence arxiv cond-mat.dis-nn cond-mat.stat-mech cs.lg dynamics however intelligence key machine machine learning making physics.chem-ph physics.comp-ph prior probability representation representation learning through type