Inference of Abstraction for a Unified Account of Reasoning and Learning

arXiv:2402.09046v1 Announce Type: cross
Abstract: Inspired by Bayesian approaches to brain function in neuroscience, we give a simple theory of probabilistic inference for a unified account of reasoning and learning. We simply model how data cause symbolic knowledge in terms of its satisfiability in formal logic. The underlying idea is that reasoning is a process of deriving symbolic knowledge from data via abstraction, i.e., selective ignorance. The logical consequence relation is discussed for its proof-based theoretical correctness. The MNIST dataset …

abstract abstraction arxiv bayesian brain cs.ai cs.lg cs.lo data function inference knowledge logic neuroscience reasoning simple terms theory type