Implementing structure mapping as a prior in deep learning models for abstract reasoning

Event Information

Recording

Available

Host

Analogical Minds

Duration

90 minutes

Abstract

Building conceptual abstractions from sensory information and then reasoning about them is central to human intelligence. Abstract reasoning both relies on, and is facilitated by, our ability to make analogies about concepts from known domains to novel domains. Structure Mapping Theory of human analogical reasoning posits that analogical mappings rely on (higher-order) relations and not on the sensory content of the domain. This enables humans to reason systematically about novel domains, a problem with which machine learning (ML) models tend to struggle. We introduce a two-stage neural net framework, which we label Neural Structure Mapping (NSM), to learn visual analogies from Raven's Progressive Matrices, an abstract visual reasoning test of fluid intelligence. Our framework uses (1) a multi-task visual relationship encoder to extract constituent concepts from raw visual input in the source domain, and (2) a neural module net analogy inference engine to reason compositionally about the inferred relation in the target domain. Our NSM approach (a) isolates the relational structure from the source domain with high accuracy, and (b) successfully utilizes this structure for analogical reasoning in the target domain.

Topics

Raven's Progressive Matrices abstract reasoning analogical reasoning analogy inference artificial intelligence deep learning machine learning multi-task encoder neural networks relational structure structure mapping visual analogies

Implementing structure mapping as a prior in deep learning models for abstract reasoning

Recording

Video on demand

Event Information

Abstract

Topics

Related Seminars

Related Job Opportunities