Neural-Symbolic Recursive Machine for Systematic Generalization

arXiv:2210.01603v2 Announce Type: replace
Abstract: Current learning models often struggle with human-like systematic generalization, particularly in learning compositional rules from limited data and extrapolating them to novel combinations. We introduce the Neural-Symbolic Recursive Machine (NSR), whose core is a Grounded Symbol System (GSS), allowing for the emergence of combinatorial syntax and semantics directly from training data. The NSR employs a modular design that integrates neural perception, syntactic parsing, and semantic reasoning. These components are synergistically trained through a novel deduction-abduction …

abstract arxiv core cs.cl cs.cv cs.lg current data emergence human human-like machine novel recursive rules semantics struggle syntax them type