19 Jul Neural Abstract Reasoner
Abstract reasoning and logic inference are diﬃcult problems for neural networks, yet essential to their applicability in highly structured domains. In this work we demonstrate that a well known technique such as spectral regularization can signiﬁcantly boost the capabilities of a neural learner. We introduce the Neural Abstract Reasoner (NAR), a memory augmented architecture capable of learning and using abstract rules. We show that, when trained with spectral regularization, NAR achieves 61.13% accuracy on the Abstraction and Reasoning Corpus. We provide intuition for the eﬀects of spectral regularization in the domain of abstract reasoning based on theoretical generalization bounds and Solomonoﬀ’s theory of inductive inference.
Viktor Stilianov Kolev