5 papers
A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks
Ryan Pyle, Sebastian Musslick, Jonathan D. Cohen +1
A key property of neural networks (both biological and artificial) is how they learn to represent and manipulate input information in order to solve a task. Different types of repr…
Systematic Visual Reasoning through Object-Centric Relational Abstraction
Taylor W. Webb, Shanka Subhra Mondal, Jonathan D. Cohen
Human visual reasoning is characterized by an ability to identify abstract patterns from only a small number of examples, and to systematically generalize those patterns to novel i…
Determinantal Point Process Attention Over Grid Cell Code Supports Out of Distribution Generalization
Shanka Subhra Mondal, Steven Frankland, Taylor Webb +1
Deep neural networks have made tremendous gains in emulating human-like intelligence, and have been used increasingly as ways of understanding how the brain may solve the complex c…
Beyond Transformers for Function Learning
Simon Segert, Jonathan Cohen
The ability to learn and predict simple functions is a key aspect of human intelligence. Recent works have started to explore this ability using transformer architectures, however…
Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
Awni Altabaa, Taylor Webb, Jonathan Cohen +1
An extension of Transformers is proposed that enables explicit relational reasoning through a novel module called the Abstractor. At the core of the Abstractor is a variant of atte…