Alert button
Picture for Maithra Raghu

Maithra Raghu

Alert button

Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures

May 26, 2022
Emmanuel Abbe, Samy Bengio, Elisabetta Cornacchia, Jon Kleinberg, Aryo Lotfi, Maithra Raghu, Chiyuan Zhang

Figure 1 for Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
Figure 2 for Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
Figure 3 for Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
Figure 4 for Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
Viaarxiv icon

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

Feb 15, 2022
Thao Nguyen, Maithra Raghu, Simon Kornblith

Figure 1 for On the Origins of the Block Structure Phenomenon in Neural Network Representations
Figure 2 for On the Origins of the Block Structure Phenomenon in Neural Network Representations
Figure 3 for On the Origins of the Block Structure Phenomenon in Neural Network Representations
Figure 4 for On the Origins of the Block Structure Phenomenon in Neural Network Representations
Viaarxiv icon

Do Vision Transformers See Like Convolutional Neural Networks?

Aug 19, 2021
Maithra Raghu, Thomas Unterthiner, Simon Kornblith, Chiyuan Zhang, Alexey Dosovitskiy

Figure 1 for Do Vision Transformers See Like Convolutional Neural Networks?
Figure 2 for Do Vision Transformers See Like Convolutional Neural Networks?
Figure 3 for Do Vision Transformers See Like Convolutional Neural Networks?
Figure 4 for Do Vision Transformers See Like Convolutional Neural Networks?
Viaarxiv icon

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

Jul 27, 2021
Chiyuan Zhang, Maithra Raghu, Jon Kleinberg, Samy Bengio

Figure 1 for Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization
Figure 2 for Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization
Figure 3 for Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization
Figure 4 for Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization
Viaarxiv icon

Teaching with Commentaries

Nov 05, 2020
Aniruddh Raghu, Maithra Raghu, Simon Kornblith, David Duvenaud, Geoffrey Hinton

Figure 1 for Teaching with Commentaries
Figure 2 for Teaching with Commentaries
Figure 3 for Teaching with Commentaries
Figure 4 for Teaching with Commentaries
Viaarxiv icon

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

Oct 29, 2020
Thao Nguyen, Maithra Raghu, Simon Kornblith

Figure 1 for Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
Figure 2 for Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
Figure 3 for Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
Figure 4 for Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
Viaarxiv icon

Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics

Jul 14, 2020
Vinay V. Ramasesh, Ethan Dyer, Maithra Raghu

Figure 1 for Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
Figure 2 for Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
Figure 3 for Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
Figure 4 for Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
Viaarxiv icon

A Survey of Deep Learning for Scientific Discovery

Mar 26, 2020
Maithra Raghu, Eric Schmidt

Figure 1 for A Survey of Deep Learning for Scientific Discovery
Figure 2 for A Survey of Deep Learning for Scientific Discovery
Figure 3 for A Survey of Deep Learning for Scientific Discovery
Figure 4 for A Survey of Deep Learning for Scientific Discovery
Viaarxiv icon

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

Sep 19, 2019
Aniruddh Raghu, Maithra Raghu, Samy Bengio, Oriol Vinyals

Figure 1 for Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
Figure 2 for Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
Figure 3 for Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
Figure 4 for Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
Viaarxiv icon

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

Mar 28, 2019
Maithra Raghu, Katy Blumer, Greg Corrado, Jon Kleinberg, Ziad Obermeyer, Sendhil Mullainathan

Figure 1 for The Algorithmic Automation Problem: Prediction, Triage, and Human Effort
Figure 2 for The Algorithmic Automation Problem: Prediction, Triage, and Human Effort
Figure 3 for The Algorithmic Automation Problem: Prediction, Triage, and Human Effort
Figure 4 for The Algorithmic Automation Problem: Prediction, Triage, and Human Effort
Viaarxiv icon