Thomas Serre

Thomas Serre

Brown University

H-index: 46

North America-United States

About Thomas Serre

Thomas Serre, With an exceptional h-index of 46 and a recent h-index of 35 (since 2020), a distinguished researcher at Brown University, specializes in the field of computational neuroscience, computer vision, computational behavioral science, deep learning, recurrent neural networks.

His recent articles reflect a diverse array of research interests and contributions to the field:

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

A holistic approach to unifying automatic concept extraction and concept importance estimation

Unlocking feature visualization for deep network with MAgnitude constrained optimization

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

Learning Functional Transduction

Craft: Concept recursive activation factorization for explainability

Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis

Break it down: Evidence for structural compositionality in neural networks

Thomas Serre Information

University

Position

and ANR-3IA Artificial and Natural Intelligence Toulouse Institute

Citations(all)

17820

Citations(since 2020)

7815

Cited By

12971

hIndex(all)

46

hIndex(since 2020)

35

i10Index(all)

85

i10Index(since 2020)

67

Email

University Profile Page

Google Scholar

Thomas Serre Skills & Research Interests

computational neuroscience

computer vision

computational behavioral science

deep learning

recurrent neural networks

Top articles of Thomas Serre

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

Advances in Neural Information Processing Systems

2024/2/13

A holistic approach to unifying automatic concept extraction and concept importance estimation

Advances in Neural Information Processing Systems

2024/2/13

Unlocking feature visualization for deep network with MAgnitude constrained optimization

Advances in Neural Information Processing Systems

2024/2/13

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

Advances in Neural Information Processing Systems

2024/2/13

Learning Functional Transduction

Advances in Neural Information Processing Systems

2024/2/13

Thomas Serre
Thomas Serre

H-Index: 33

Craft: Concept recursive activation factorization for explainability

2023

Thomas Fel
Thomas Fel

H-Index: 1

Thomas Serre
Thomas Serre

H-Index: 33

Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis

2023

Thomas Fel
Thomas Fel

H-Index: 1

Thomas Serre
Thomas Serre

H-Index: 33

Break it down: Evidence for structural compositionality in neural networks

Advances in Neural Information Processing Systems

2023/12/15

Thomas Serre
Thomas Serre

H-Index: 33

Ellie Pavlick
Ellie Pavlick

H-Index: 18

Categorizing the Visual Environment and Analyzing the Visual Attention of Dogs

arXiv preprint arXiv:2311.11988

2023/11/20

Thomas Serre
Thomas Serre

H-Index: 33

Uncovering Causal Variables in Transformers using Circuit Probing

arXiv preprint arXiv:2311.04354

2023/11/7

Thomas Serre
Thomas Serre

H-Index: 33

Ellie Pavlick
Ellie Pavlick

H-Index: 18

Uncovering Intermediate Variables in Transformers using Circuit Probing

arXiv e-prints

2023/11

Thomas Serre
Thomas Serre

H-Index: 33

Ellie Pavlick
Ellie Pavlick

H-Index: 18

Fixing the problems of deep neural networks will require better training data and learning algorithms

arXiv preprint arXiv:2311.12819

2023/9/26

Drew Linsley
Drew Linsley

H-Index: 11

Thomas Serre
Thomas Serre

H-Index: 33

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

arXiv preprint arXiv:2309.13181

2023/9/22

Categorizing Dog’s Real World Visual Environment

2023/9

Thomas Serre
Thomas Serre

H-Index: 33

NeuroSurgeon: A toolkit for subnetwork analysis

arXiv preprint arXiv:2309.00244

2023/9/1

Ellie Pavlick
Ellie Pavlick

H-Index: 18

Thomas Serre
Thomas Serre

H-Index: 33

Cerebrospinal fluid transcripts may predict shunt surgery responses in normal pressure hydrocephalus

Brain

2023/9

Harmonizing the visual strategies of image-computable models with humans yields more performant and interpretable models of primate visual system function.

Journal of Vision

2023/8/1

A neural network model of category-learning induced transfer of visual perceptual learning

Journal of Vision

2023/8/1

Luke Rosedahl
Luke Rosedahl

H-Index: 3

Thomas Serre
Thomas Serre

H-Index: 33

Gradient strikes back: How filtering out high frequencies improves explanations

arXiv preprint arXiv:2307.09591

2023/7/18

Thomas Fel
Thomas Fel

H-Index: 1

Thomas Serre
Thomas Serre

H-Index: 33

Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception

arXiv preprint arXiv:2306.03229

2023/6/5

See List of Professors in Thomas Serre University(Brown University)

Co-Authors

academic-engine