research
∙
09/27/2022
Why neural networks find simple solutions: the many regularizers of geometric complexity
In many contexts, simpler models are preferable to more complex models a...
share
research
∙
11/30/2021
The Geometric Occam's Razor Implicit in Deep Learning
In over-parameterized deep neural networks there can be many possible pa...
research
∙
05/28/2021
Discretization Drift in Two-Player Games
Gradient-based methods for two-player games produce rich dynamics that c...
research
∙
01/28/2021
On the Origin of Implicit Regularization in Stochastic Gradient Descent
For infinitesimal learning rates, stochastic gradient descent (SGD) foll...
research
∙
09/23/2020
Implicit Gradient Regularization
Gradient descent can be surprisingly good at optimizing deep neural netw...
research
∙
01/31/2019
Learning to Make Analogies by Contrasting Abstract Relational Structure
Analogical reasoning has been a principal focus of various waves of AI r...
research
∙
10/31/2018
Analyzing biological and artificial neural networks: challenges with opportunities for synergy?
Deep neural networks (DNNs) transform stimuli across multiple processing...
research
∙
07/11/2018
Measuring abstract reasoning in neural networks
Whether neural networks can learn abstract reasoning or whether they mer...
research
∙
03/19/2018
On the importance of single directions for generalization
Despite their ability to memorize large datasets, deep neural networks o...
research
∙
06/26/2017
Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study
Deep neural networks (DNNs) have achieved unprecedented performance on a...
research
∙
06/05/2017