Search Results for author: Keith J. Holyoak

Found 2 papers, 0 papers with code

Visual analogy: Deep learning versus compositional models

no code implementations14 May 2021 Nicholas Ichien, Qing Liu, Shuhao Fu, Keith J. Holyoak, Alan Yuille, Hongjing Lu

We compared human performance to that of two recent deep learning models (Siamese Network and Relation Network) directly trained to solve these analogy problems, as well as to that of a compositional model that assesses relational similarity between part-based representations.

Probabilistic Analogical Mapping with Semantic Relation Networks

no code implementations30 Mar 2021 Hongjing Lu, Nicholas Ichien, Keith J. Holyoak

The human ability to flexibly reason using analogies with domain-general content depends on mechanisms for identifying relations between concepts, and for mapping concepts and their relations across analogs.

Graph Matching Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.