activity
20202022
most citedOn the geometry of generalization and memorization in deep neural networks

13 citations · 41 across the 9 of their papers we have counts for

collaborators

9 papers

stat.ML2022

The Implicit Bias of Gradient Descent on Generalized Gated Linear Networks

Samuel Lippl, L. F. Abbott, SueYeon Chung

Understanding the asymptotic behavior of gradient-descent training of deep neural networks is essential for revealing inductive biases and improving network performance. We derive…

cs.LG20211 cited

Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networks

Landan Seguin, Anthony Ndirango, Neeli Mishra +2

Adversarial defenses train deep neural networks to be invariant to the input perturbations from adversarial attacks. Almost all defense strategies achieve this invariance through a…

q-bio.NC20213 cited

Credit Assignment Through Broadcasting a Global Error Vector

David G. Clark, L. F. Abbott, SueYeon Chung

Backpropagation (BP) uses detailed, unit-specific feedback to train deep neural networks (DNNs) with remarkable success. That biological neural circuits appear to perform credit as…

q-bio.NC20212 cited

Statistical Mechanics of Neural Processing of Object Manifolds

SueYeon Chung

Invariant object recognition is one of the most fundamental cognitive tasks performed by the brain. In the neural state space, different objects with stimulus variabilities are rep…

cs.LG202113 cited

On the geometry of generalization and memorization in deep neural networks

Cory Stephenson, Suchismita Padhy, Abhinav Ganesh +3

Understanding how large neural networks avoid memorizing training data is key to explaining their high generalization performance. To examine the structure of when and where memori…

cs.CL20211 cited

Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models

Matteo Alleman, Jonathan Mamou, Miguel A Del Rio +3

While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workin…