Relation learning in a neurocomputational architecture supports cross-domain transfer

Leonidas Doumas, Guillermo Puebla Ramírez, Andrea E. Martin, John E. Hummel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Humans readily generalize, applying prior knowledge to novel situations and stimuli. Advances in machine learning have be- gun to approximate and even surpass human performance, but these systems struggle to generalize what they have learned to untrained situations. We present a model based on well- established neurocomputational principles that demonstrates human-level generalisation. This model is trained to play one video game (Breakout) and performs one-shot generalisation to a new game (Pong) with different characteristics. The model generalizes because it learns structured representations that are functionally symbolic (viz., a role-filler binding calculus) from unstructured training data. It does so without feedback, and without requiring that structured representations are specified a priori. Specifically, the model uses neural co-activation to discover which characteristics of the input are invariant and to learn relational predicates, and oscillatory regularities in net- work firing to bind predicates to arguments. To our knowledge, this is the first demonstration of human-like generalisation in a machine system that does not assume structured representations to begin with.
Original languageEnglish
Title of host publicationProceedings of the 42nd Annual Conference of the Cognitive Science Society
EditorsStephanie Denison, Michael Mack, Yang Xu, Blair C. Armstrong
PublisherCognitive Science Society
Pages932-937
Number of pages6
ISBN (Print)9781713818977
Publication statusPublished - 30 Nov 2020

Keywords / Materials (for Non-textual outputs)

  • predicate learning
  • generalisation
  • neural networks
  • symbolic-connectionism
  • neural oscillations

Fingerprint

Dive into the research topics of 'Relation learning in a neurocomputational architecture supports cross-domain transfer'. Together they form a unique fingerprint.

Cite this