activity
20162022
most citedSVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

226 citations · 316 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG20226 cited

On the Origins of the Block Structure Phenomenon in Neural Network Representations

Thao Nguyen, Maithra Raghu, Simon Kornblith

Recent work has uncovered a striking phenomenon in large-capacity neural networks: they contain blocks of contiguous hidden layers with highly similar representations. This block s…

cs.LG20204 cited

Teaching with Commentaries

Aniruddh Raghu, Maithra Raghu, Simon Kornblith +2

Effective training of deep neural networks can be challenging, and there remain many open questions on how to best learn these models. Recently developed methods to improve neural…

cs.LG2020

Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth

Thao Nguyen, Maithra Raghu, Simon Kornblith

A key factor in the success of deep neural networks is the ability to scale models to improve performance by varying the architecture depth and width. This simple property of neura…

cs.LG202022 cited

Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics

Vinay V. Ramasesh, Ethan Dyer, Maithra Raghu

A central challenge in developing versatile machine learning systems is catastrophic forgetting: a model trained on tasks in sequence will suffer significant performance drops on e…

cs.LG2020

A Survey of Deep Learning for Scientific Discovery

Maithra Raghu, Eric Schmidt

Over the past few years, we have seen fundamental breakthroughs in core problems in machine learning, largely driven by advances in deep neural networks. At the same time, the amou…

cs.LG2019

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML

Aniruddh Raghu, Maithra Raghu, Samy Bengio +1

An important research direction in machine learning has centered around developing meta-learning algorithms to tackle few-shot learning. An especially successful algorithm has been…