Bridging Associative Memory and Probabilistic Modeling

arXiv:2402.10202v1 Announce Type: new
Abstract: Associative memory and probabilistic modeling are two fundamental topics in artificial intelligence. The first studies recurrent neural networks designed to denoise, complete and retrieve data, whereas the second studies learning and sampling from probability distributions. Based on the observation that associative memory's energy functions can be seen as probabilistic modeling's negative log likelihoods, we build a bridge between the two that enables useful flow of ideas in both directions. We showcase four examples: First, we …

abstract artificial artificial intelligence arxiv cs.lg data energy functions intelligence memory modeling networks neural networks observation probabilistic modeling probability recurrent neural networks sampling studies topics type