Search Results for author:
Found 7 papers, 6 papers with code
Evidence from counterfactual tasks supports emergent analogical reasoning in large language models
We recently reported evidence that large language models are capable of solving a wide range of text-based analogy problems in a zero-shot manner, indicating the presence of an emergent capacity for analogical reasoning.
A Prefrontal Cortex-inspired Architecture for Planning in Large Language Models
To address this, we take inspiration from the human brain, in which planning is accomplished via the recurrent interaction of specialized modules in the prefrontal cortex (PFC).
Determinantal Point Process Attention Over Grid Cell Code Supports Out of Distribution Generalization
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 computational problems on which this relies.
Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
An extension of Transformers is proposed that enables explicit relational reasoning through a novel module called the Abstractor.
Learning to reason over visual objects
These results suggest that an inductive bias for object-centric processing may be a key component of abstract visual reasoning, obviating the need for problem-specific inductive biases.
Emergent Analogical Reasoning in Large Language Models
In human cognition, this capacity is closely tied to an ability to reason by analogy.
Modelling the development of counting with memory-augmented neural networks
Learning to count is an important example of the broader human capacity for systematic generalization, and the development of counting is often characterized by an inflection point when children rapidly acquire proficiency with the procedures that support this ability.
