Technical Program

Paper Detail

Paper: PS-2B.12
Session: Poster Session 2B
Location: H Fl├Ąche 1.OG
Session Time: Sunday, September 15, 17:15 - 20:15
Presentation Time:Sunday, September 15, 17:15 - 20:15
Presentation: Poster
Publication: 2019 Conference on Cognitive Computational Neuroscience, 13-16 September 2019, Berlin, Germany
Paper Title: Predicate learning via neural oscillations supports one-shot generalization between video games
Manuscript:  Click here to view manuscript
License: Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
Authors: Leonidas A. A. Doumas, Guillermo Puebla, University of Edinburgh, United Kingdom; John E. Hummel, University of Illinois, United States; Andrea E. Martin, Max Planck Institute for Psycholinguistics, Netherlands
Abstract: Humans readily generalize, applying prior knowledge to novel situations and stimuli. Advances in machine learning have begun 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 generalization. This model is trained to play one video game (Breakout) and performs one-shot generalization 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 network firing to bind predicates to arguments. To our knowledge, this is the first demonstration of human-like generalization in a machine system that does not assume structured representations to begin with.