Alert button
Picture for Thomas Serre

Thomas Serre

Alert button

Categorizing the Visual Environment and Analyzing the Visual Attention of Dogs

Nov 20, 2023
Shreyas Sundara Raman, Madeline H. Pelgrim, Daphna Buchsbaum, Thomas Serre

Viaarxiv icon

Uncovering Intermediate Variables in Transformers using Circuit Probing

Nov 17, 2023
Michael A. Lepori, Thomas Serre, Ellie Pavlick

Viaarxiv icon

Uncovering Causal Variables in Transformers using Circuit Probing

Nov 07, 2023
Michael A. Lepori, Thomas Serre, Ellie Pavlick

Viaarxiv icon

Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning

Sep 22, 2023
Lakshmi Narasimhan Govindarajan, Rex G Liu, Drew Linsley, Alekh Karkada Ashok, Max Reuter, Michael J Frank, Thomas Serre

Viaarxiv icon

NeuroSurgeon: A Toolkit for Subnetwork Analysis

Sep 01, 2023
Michael A. Lepori, Ellie Pavlick, Thomas Serre

Viaarxiv icon

Gradient strikes back: How filtering out high frequencies improves explanations

Jul 18, 2023
Sabine Muzellec, Leo Andeol, Thomas Fel, Rufin VanRullen, Thomas Serre

Figure 1 for Gradient strikes back: How filtering out high frequencies improves explanations
Figure 2 for Gradient strikes back: How filtering out high frequencies improves explanations
Figure 3 for Gradient strikes back: How filtering out high frequencies improves explanations
Figure 4 for Gradient strikes back: How filtering out high frequencies improves explanations
Viaarxiv icon

Computing a human-like reaction time metric from stable recurrent vision models

Jun 20, 2023
Lore Goetschalckx, Lakshmi Narasimhan Govindarajan, Alekh Karkada Ashok, Aarit Ahuja, David L. Sheinberg, Thomas Serre

Figure 1 for Computing a human-like reaction time metric from stable recurrent vision models
Figure 2 for Computing a human-like reaction time metric from stable recurrent vision models
Figure 3 for Computing a human-like reaction time metric from stable recurrent vision models
Figure 4 for Computing a human-like reaction time metric from stable recurrent vision models
Viaarxiv icon

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization

Jun 11, 2023
Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Picard, Paul Novello, Julien Colin, Drew Linsley, Tom Rousseau, Rémi Cadène, Laurent Gardes, Thomas Serre

Figure 1 for Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Figure 2 for Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Figure 3 for Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Figure 4 for Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Viaarxiv icon

A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation

Jun 11, 2023
Thomas Fel, Victor Boutin, Mazda Moayeri, Rémi Cadène, Louis Bethune, Léo andéol, Mathieu Chalvidal, Thomas Serre

Figure 1 for A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
Figure 2 for A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
Figure 3 for A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
Figure 4 for A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
Viaarxiv icon

Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex

Jun 06, 2023
Drew Linsley, Ivan F. Rodriguez, Thomas Fel, Michael Arcaro, Saloni Sharma, Margaret Livingstone, Thomas Serre

Figure 1 for Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex
Figure 2 for Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex
Figure 3 for Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex
Figure 4 for Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex
Viaarxiv icon