Maithra Raghu

is this you? claim profile

∙ 0 followers
Google ∙ MIT

Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization

The successes of deep learning critically rely on the ability of neural ...
07/27/2021 ∙ by Chiyuan Zhang, et al. ∙ 16 ∙ share

read it
Teaching with Commentaries

Effective training of deep neural networks can be challenging, and there...
11/05/2020 ∙ by Aniruddh Raghu, et al. ∙ 3 ∙ share

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

A key factor in the success of deep neural networks is the ability to sc...
10/29/2020 ∙ by Thao Nguyen, et al. ∙ 73 ∙ share

read it
Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics

A central challenge in developing versatile machine learning systems is ...
07/14/2020 ∙ by Vinay V. Ramasesh, et al. ∙ 0 ∙ share

read it
A Survey of Deep Learning for Scientific Discovery

Over the past few years, we have seen fundamental breakthroughs in core ...
03/26/2020 ∙ by Maithra Raghu, et al. ∙ 76 ∙ share

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

An important research direction in machine learning has centered around ...
09/19/2019 ∙ by Aniruddh Raghu, et al. ∙ 5 ∙ share

read it
The Algorithmic Automation Problem: Prediction, Triage, and Human Effort

In a wide array of areas, algorithms are matching and surpassing the per...
03/28/2019 ∙ by Maithra Raghu, et al. ∙ 8 ∙ share

read it
Transfusion: Understanding Transfer Learning with Applications to Medical Imaging

With the increasingly varied applications of deep learning, transfer lea...
02/14/2019 ∙ by Maithra Raghu, et al. ∙ 26 ∙ share

read it
Direct Uncertainty Prediction with Applications to Healthcare

Large labeled datasets for supervised learning are frequently constructe...
07/04/2018 ∙ by Maithra Raghu, et al. ∙ 0 ∙ share

read it
Insights on representational similarity in neural networks with canonical correlation

Comparing different neural network representations and determining how r...
06/14/2018 ∙ by Ari S. Morcos, et al. ∙ 0 ∙ share

read it
Adversarial Spheres

State of the art computer vision models have been shown to be vulnerable...
01/09/2018 ∙ by Justin Gilmer, et al. ∙ 0 ∙ share

read it
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?

Deep reinforcement learning has achieved many recent successes, but our ...
11/07/2017 ∙ by Maithra Raghu, et al. ∙ 0 ∙ share

read it
SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

We propose a new technique, Singular Vector Canonical Correlation Analys...
06/19/2017 ∙ by Maithra Raghu, et al. ∙ 0 ∙ share

read it
Linear Additive Markov Processes

We introduce LAMP: the Linear Additive Markov Process. Transitions in LA...
04/05/2017 ∙ by Ravi Kumar, et al. ∙ 0 ∙ share

read it
Survey of Expressivity in Deep Neural Networks

We survey results on neural network expressivity described in "On the Ex...
11/24/2016 ∙ by Maithra Raghu, et al. ∙ 0 ∙ share

read it
Exponential expressivity in deep neural networks through transient chaos

We combine Riemannian geometry with the mean field theory of high dimens...
06/16/2016 ∙ by Ben Poole, et al. ∙ 0 ∙ share

read it
On the Expressive Power of Deep Neural Networks

We propose a new approach to the problem of neural network expressivity,...
06/16/2016 ∙ by Maithra Raghu, et al. ∙ 0 ∙ share

read it

Maithra Raghu

Featured Co-authors

Quoc V. Le

Oriol Vinyals

Jascha Sohl-Dickstein

Jon Kleinberg

Ian Goodfellow

Samy Bengio

David Duvenaud

Surya Ganguli

Jacob Andreas

Ravi Kumar

Geoffrey Hinton

Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization

Teaching with Commentaries

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

Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics

A Survey of Deep Learning for Scientific Discovery

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

The Algorithmic Automation Problem: Prediction, Triage, and Human Effort

Transfusion: Understanding Transfer Learning with Applications to Medical Imaging

Direct Uncertainty Prediction with Applications to Healthcare

Insights on representational similarity in neural networks with canonical correlation

Adversarial Spheres

Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?

SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

Linear Additive Markov Processes

Survey of Expressivity in Deep Neural Networks

Exponential expressivity in deep neural networks through transient chaos

On the Expressive Power of Deep Neural Networks