167 citations · 268 across the 15 of their papers we have counts for
17 papers
Parameter symmetries determine representational geometry in overparameterized nonlinear networks
Marvin Theiss, Lukas Braun, Andrew M. Saxe +1
Representations are routinely used across machine learning, psychology, and neuroscience to draw inferences about the computations of biological and artificial systems. Such infere…
Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks
Lukas Braun, Erin Grant, Andrew M. Saxe
A foundational principle of connectionism is that perception, action, and cognition emerge from parallel computations among simple, interconnected units that generate and rely on n…
Nonlinear dynamics of localization in neural receptive fields
Leon Lufkin, Andrew M. Saxe, Erin Grant
Localized receptive fields -- neurons that are selective for certain contiguous spatiotemporal features of their input -- populate early sensory regions of the mammalian brain. Uns…
The Transient Nature of Emergent In-Context Learning in Transformers
Aaditya K. Singh, Stephanie C. Y. Chan, Ted Moskovitz +3
Transformer neural networks can exhibit a surprising capacity for in-context learning (ICL) despite not being explicitly trained for it. Prior work has provided a deeper understand…
Bayes in the age of intelligent machines
Thomas L. Griffiths, Jian-Qiao Zhu, Erin Grant +1
The success of methods based on artificial neural networks in creating intelligent machines seems like it might pose a challenge to explanations of human cognition in terms of Baye…
Getting aligned on representational alignment
Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller +30
Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we m…
Statistical physics, Bayesian inference and neural information processing
Erin Grant, Sandra Nestler, Berfin Şimşek +1
Lecture notes from the course given by Professor Sara A. Solla at the Les Houches summer school on "Statistical physics of Machine Learning". The notes discuss neural information p…
Gaussian Process Surrogate Models for Neural Networks
Michael Y. Li, Erin Grant, Thomas L. Griffiths
Not being able to understand and predict the behavior of deep learning systems makes it hard to decide what architecture and algorithm to use for a given problem. In science and en…
Distinguishing rule- and exemplar-based generalization in learning systems
Ishita Dasgupta, Erin Grant, Thomas L. Griffiths
Machine learning systems often do not share the same inductive biases as humans and, as a result, extrapolate or generalize in ways that are inconsistent with our expectations. The…
Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity
Thomas A. Langlois, H. Charles Zhao, Erin Grant +3
Developments in machine learning interpretability techniques over the past decade have provided new tools to observe the image regions that are most informative for classification…
Are Convolutional Neural Networks or Transformers more like human vision?
Shikhar Tuli, Ishita Dasgupta, Erin Grant +1
Modern machine learning models for computer vision exceed humans in accuracy on specific visual recognition tasks, notably on datasets like ImageNet. However, high accuracy can be…
Connecting Context-specific Adaptation in Humans to Meta-learning
Rachit Dubey, Erin Grant, Michael Luo +2
Cognitive control, the ability of a system to adapt to the demands of a task, is an integral part of cognition. A widely accepted fact about cognitive control is that it is context…
Universal linguistic inductive biases via meta-learning
R. Thomas McCoy, Erin Grant, Paul Smolensky +2
How do learners acquire languages from the limited data available to them? This process must involve some inductive biases - factors that affect how a learner generalizes - but it…
Reconciling meta-learning and continual learning with online mixtures of tasks
Ghassen Jerfel, Erin Grant, Thomas L. Griffiths +1
Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is…
Evaluating Theory of Mind in Question Answering
Aida Nematzadeh, Kaylee Burns, Erin Grant +2
We propose a new dataset for evaluating question answering models with respect to their capacity to reason about beliefs. Our tasks are inspired by theory-of-mind experiments that…
Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
Erin Grant, Chelsea Finn, Sergey Levine +2
Meta-learning allows an intelligent agent to leverage prior learning episodes as a basis for quickly improving performance on a novel task. Bayesian hierarchical modeling provides…
The Interaction of Memory and Attention in Novel Word Generalization: A Computational Investigation
Erin Grant, Aida Nematzadeh, Suzanne Stevenson
People exhibit a tendency to generalize a novel noun to the basic-level in a hierarchical taxonomy -- a cognitively salient category such as "dog" -- with the degree of generalizat…