The relational bottleneck as an inductive bias for efficient abstraction
A central challenge for cognitive science is to explain how abstract concepts are acquired
from limited experience. This has often been framed in terms of a dichotomy between …
from limited experience. This has often been framed in terms of a dichotomy between …
Emergent analogical reasoning in large language models
The recent advent of large language models has reinvigorated debate over whether human
cognitive capacities might emerge in such generic models given sufficient training data. Of …
cognitive capacities might emerge in such generic models given sufficient training data. Of …
[HTML][HTML] Transfer learning and analogical inference: A critical comparison of algorithms, methods, and applications
Artificial intelligence and machine learning (AI/ML) research has aimed to achieve human-
level performance in tasks that require understanding and decision making. Although major …
level performance in tasks that require understanding and decision making. Although major …
[HTML][HTML] Semantic regularization of electromagnetic inverse problems
H Zhang, Y Chen, Z Wang, TJ Cui… - Nature …, 2024 - nature.com
Solving ill-posed inverse problems typically requires regularization based on prior
knowledge. To date, only prior knowledge that is formulated mathematically (eg, sparsity of …
knowledge. To date, only prior knowledge that is formulated mathematically (eg, sparsity of …
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 …
range of text-based analogy problems in a zero-shot manner, indicating the presence of an …
[HTML][HTML] 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 …
and have been used increasingly as ways of understanding how the brain may solve the …
A Human-factors Approach for Evaluating AI-generated Images
As generative artificial intelligence (AI) becomes more common in day-to-day life, AI-
generated content (AIGC) needs to be accurate, relevant, and comprehensive. These …
generated content (AIGC) needs to be accurate, relevant, and comprehensive. These …
[PDF][PDF] Shape Guides Visual Pretense
People often imagine everyday objects are something else. A turned over bottle becomes a
car, a teapot becomes a swan. Such pretense is common in play, pedagogy, and narratives …
car, a teapot becomes a swan. Such pretense is common in play, pedagogy, and narratives …
Hierarchical Perceptual and Predictive Analogy-Inference Network for Abstract Visual Reasoning
Advances in computer vision research enable human-like high-dimensional perceptual
induction over analogical visual reasoning problems, such as Raven's Progressive Matrices …
induction over analogical visual reasoning problems, such as Raven's Progressive Matrices …
Analogy as Nonparametric Bayesian Inference over Relational Systems
RM Battleday, TL Griffiths - arXiv preprint arXiv:2006.04156, 2020 - arxiv.org
Much of human learning and inference can be framed within the computational problem of
relational generalization. In this project, we propose a Bayesian model that generalizes …
relational generalization. In this project, we propose a Bayesian model that generalizes …