A Brown University Research Group

    Work in progress

  1. Monkeys engage in visual simulation to solve complex problems

    bioRxiv

    A. Ahuja, N.Y. Rodriguez, A.K. Ashok, T. Serre, T. Desrochers, D. Sheinberg

  2. Uncovering intermediate variables in transformers using circuit probing

    arXiv

    MA. Lepori, T. Serre & E. Pavlick

  3. Categorizing the visual environment and analyzing the visual attention of dogs

    arXiv

    S.S Raman, M.H. Pelgrim, D. Buchsbaum & T. Serre

  4. Gradient strikes back: How filtering out high frequencies improves explanations

    arXiv

    S. Muzellec, L. Andeol, T. Fel, R. VanRullen & T. Serre

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

    arXiv

    D. Linsley, P. Feng, T. Boissin, A.K. Ashok, T. Fel, S. Olaiya, T. Serre

  6. Deceptive learning in histopathology

    biorXiv

    S. Shahamatdar*, D. Saeed-Vafa*, D. Linsley*, F. Khalil, K. Lovinger, L. Li, H. McLeod, S. Ramachandran**, T. Serre**

    2023

  1. Ecological data and objectives align deep neural network representations with humans

    "UniReps: Unifying Representations in Neural Models" NeurIPS workshop

    A. Nagaraj, A.K. Ashok, D. Linsley, F.E Lewis, P. Zhou & T. Serre

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

    Behavioral & Brain Sciences

    T. Serre & D. Linsley

  3. Unlocking feature visualization for deeper networks with magnitude constrained optimization

    Neural Information Processing Systems

    T. Fel, T. Boissin, V. Boutin, A. Picard, P. Novello, J. Colin, D. Linsley, T. Rousseau, R. Cadène, L. Gardes & T. Serre

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

    Neural Information Processing Systems

    L. Goetschalckx, L.N. Govindarajan, A.K. Ashok, A. Ahuja, D.L. Sheinberg & T. Serre

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

    Neural Information Processing Systems

    T. Fel, V. Boutin, M. Moayeri, R. Cadene, L. Bethune, L. Andeol, M. Chalvidal & T. Serre

  6. Break it down: Evidence for structural compositionality in neural networks

    Neural Information Processing Systems

    M.A. Lepori, T. Serre & E. Pavlick

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

    Neural Information Processing Systems

    D. Linsley, I.F. Rodriguez, T. Fel, M. Arcaro, S. Sharma, M. Livingstone & T. Serre

  8. Learning functional transduction

    Neural Information Processing Systems

    M. Chalvidal, T. Serre & R.VanRullen

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

    arXiv

    L.N. Govindarajan, R.G. Liu, D. Linsley, A.K. Ashok, M. Reuter, M.J. Frank & T. Serre

  10. Diffusion models as artists: Are we closing the gap between humans and machines?

    International Conference on Machine Learning

    V. Boutin, T. Fel, L. Singhal, R. Mukherji, A. Nagaraj, J Colin & T. Serre

  11. CRAFT: Concept Recursive Activation FacTorization for explainability

    IEEE Conference on Computer Vision and Pattern Recognition

    T. Fel, A. Picard, L. Bethune, T. Boissin, D. Vigouroux, J. Colin, R. Cadene & T. Serre

  12. Transcriptomic profiling of cerebrospinal fluid predicts shunt surgery responses in patients with normal pressure hydrocephalus

    Brain

    Z. Levin, O.P. Leary, V. Mora, S. Kant, S. Brown, K. Svokos, U. Akbar, T. Serre, P. Klinge, A. Fleischmann, M.G. Ruocco

  13. GAMR: A Guided Attention Model for (visual) Reasoning

    International Conference on Learning Representations

    M Vaishnav & T. Serre

  14. Don’t lie to me! Robust and efficient explainability with verified perturbation analysis

    IEEE Conference on Computer Vision and Pattern Recognition

    T. Fel, M. Ducoffe, D. Vigouroux, R. Cadène, M. Capelle, C. Nicodème, T. Serre

    2022

  1. The emergence of visual simulation in task-optimized recurrent neural networks

    NeurIPS Workshop on Shared Visual Representations in Human & Machine Intelligence

    A.K. Ashok, L.N. Govindarajan, D. Linsley, D. Sheinber & T. Serre. T

  2. Fast inference of spinal neuromodulation for motor control using amortized neural networks

    Journal of Neural Engineering

    L.N. Govindarajan, J.S. Calvert, S.R. Parker, M. Jung, R. Darie, P. Miranda, E. Shaaya, D.A. Borton* & T. Serre*

  3. What I cannot predict, I do not understand: A human-centered evaluation framework for explainability methods

    Neural Information Processing Systems

    T. Fel, J. Colin, R. Cadene & T. Serre

  4. Harmonizing the object recognition strategies of deep neural networks with humans

    Neural Information Processing Systems

    T. Fel*, I.F. Rodriguez*, D. Linsley* & T. Serre

  5. A benchmark for compositional visual reasoning

    Neural Information Processing Systems

    A. Zerroug, M. Vaishnav, J. Colin, S. Musslick & T. Serre

  6. Meta-reinforcement learning with self-modifying networks

    Neural Information Processing Systems

    M. Chalvidal, T. Serre, R. VanRullen

  7. Diversity vs. recognizability: Human-like generalization in one-shot generative models

    Neural Information Processing Systems

    V. Boutin, L. Singhal, X. Thomas & T. Serre

  8. A practitioner’s guide to improve the logistics of spatiotemporal deep neural networks

    Workshop on visual observation and analysis of Vertebrate And Insect Behavior (VAIB)

    L.N. Govindarajan, R. Kakodkar & T. Serre

  9. Xplique: A deep learning explainability toolbox

    CVPR workshop on XAI4CV: Explainable Artificial Intelligence for Computer Vision

    T. Fel, L. Hervier, D. Vigouroux, A. Poche, J. Plakoo, R. Cadene, M. Chalvidal, J. Colin, T.. Boissin, L. Bethune, A. Picard, C. Nicodeme, L. Gardes, G. Flandin & T. Serre

  10. Decoding family-level features for modern and fossil leaves from computer-vision heat maps

    American Journal of Botany

    E.J. Spagnuolo, P. Wilf & T. Serre

  11. How and what to learn: Taxonomizing self-supervised learning for 3D action recognition

    Winter Conference on Applications of Computer Vision

    A. Ben Tanfous, A. Zerroug, D. Linsley & T. Serre

  12. How good is your explanation? Algorithmic stability measures to assess the quality of explanations for deep neural networks

    Winter Conference on Applications of Computer Vision

    T Fel, D. Vigouroux, R. Cadene & T. Serre

  13. Understanding the computational demands underlying visual reasoning

    Neural Computation

    M.Vaishnav, R. Cadene, A. Alamia, D. Linsley, R. VanRullen & T. Serre

    2021

  1. Super-human cell death detection with biomarker-optimized neural networks

    Science Advances

    J.W. Linsley, D.A. Linsley, J. Lamstein, G. Ryan, K. Shah, N.A. Castello, V. Oza, J. Kalra, S. Wang, Z. Tokuno, A. Javaherian, T. Serre & S. Finkbeiner

  2. Look at the variance! Efficient black-box explanations with Sobol-based sensitivity analysis

    Neural Information Processing Systems

    T. Fel, R. Cadene, M. Chalvidal, M. Cord, D. Vigouroux & T. Serre.

  3. KuraNet: systems of coupled oscillators that learn to synchronize

    arXiv

    M. Ricci, M. Jung, Y. Zhang, M. Chalvidal, A. Soni & T. Serre

  4. Tracking without re-recognition in humans and machines

    Neural Information Processing Systems

    D. Linsley*, G. Malik*, J.K. Kim, L.N. Govindarajan, E. Mingolla^, T. Serre^

  5. The challenge of appearance-free object tracking with feedforward neural networks

    CVPR Workshop on Dynamic Neural Networks Meets Computer Vision

    G. Malik, D. Linsley, T. Serre & E. Mingolla

  6. An image dataset of cleared, x-rayed, and fossil leaves vetted to plant family for human and machine learning

    PhytoKeys

    P. Wilf, S.L. Wing, H.W. Meyer, J.A. Rose, R. Saha, T. Serre, N.R. Cúneo, M.P. Donovan, D.M. Erwin, M.A. Gandolfo, E. González-Akre, F. Herrera, S. Hu, A. Iglesias, K.R. Johnson, T.S. Karim & X. Zou

  7. Deep learning networks and visual perception

    Oxford Research Encyclopedia of Psychology

    G. Lindsay & T. Serre

  8. Go with the flow: Adaptive control for Neural ODEs

    International Conference on Learning Representations

    M. Chalvidal, M. Ricci, R. VanRullen, T. Serre

  9. Using computational analysis of behavior to discover developmental change in memory-guided attention mechanisms in childhood

    psychArXiv

    D. Amso, L. Govindarajan, P. Gupta, H. Baumgartner, A. Lynn, K. Gunther, D. Placido, T. Sharma, V. Veerabadran, K. Thakkar, S. Kim & T. Serre

    2020

  1. Iterative VAE as a predictive brain model for out-of-distribution generalization

    NeurIPS workshop on Shared Visual Representations in Human and Machine Intelligence (SVRHM)

    V. Boutin, A. Zerroug, M. Jung, & Thomas Serre

  2. Same-different conceptualization: A machine vision perspective

    Current Opinion in Behavioral Sciences

    M. Ricci, R. Cadene & T. Serre

  3. Stable and expressive recurrent vision models

    Neural Information Processing Systems

    D. Linsley, A.K. Ashok, L.N. Govindarajan, R. Liu & T. Serre

  4. Hierarchical models of the visual system

    Encyclopedia of Computational Neuroscience

    M. Ricci & T. Serre

  5. Discriminating between sleep and exercise-induced fatigue using computer vision and behavioral genetics

    Journal of Neurogenetics

    K.N. Schuch†, L.N. Govindarajan,†, Y. Guo, S.N. Baskoylu, S. Kim, B. Kimia, T. Serre‡, & A.C. Hart‡

  6. Differential involvement of EEG oscillatory components in sameness vs. spatial-relation visual reasoning tasks

    eNeuro

    A. Alamia, C. Luo, M. Ricci, J. Kim, T. Serre & R. VanRullen

  7. Beyond the feedforward sweep: feedback computations in the visual cortex

    The Year in Cognitive Neuroscience

    G. Kreiman & T. Serre

  8. Disentangling neural mechanisms for perceptual grouping

    International Conference on Learning Representations

    J.K. Kim*, D. Linsley*, K. Thakkar & T. Serre

  9. Recurrent neural circuits for contours detection

    International Conference on Learning Representations

    D. Linsley*, J.K. Kim*, A. Ashok & T. Serre

    2019

  1. Development of a deep learning algorithm for the histopathologic diagnosis and gleason grading of prostate cancer biopsies: A pilot study

    European urology focus

    O. Kott*, D. Linsley*, A. Karagounis, C. Jeffers, G. Dragan, Ali Amin, T. Serre** & B. Gershman**

  2. Deep learning: the good, the bad and the ugly

    Annual Review of Vision Science

    T. Serre & S. Leone

  3. Learning what and where to attend

    International Conference on Learning Representations

    D. Linsley, D. Schiebler, S. Eberhardt & T. Serre

    2018

  1. Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks

    ArXiv

    D. Linsley, J.K. Kim, D. Berson & T. Serre

  2. Early life stress leads to sex differences in development of depressive-like outcomes in a mouse model

    Neuropsychopharmacology

    H. Goodwill, G. Manzano-Nieves, M. Gallo, H.I. Lee, E. Oyerinde, T. Serre & K. Bath

  3. Robust pose tracking with a joint model of appearance and shape

    Arxiv

    Y. Guo, L.N. Govindarajan, B. Kimia & T. Serre

  4. Learning long-range spatial dependencies with horizontal gated-recurrent units

    Neural Information Processing Systems

    D. Linsley, J. Kim, V. Veerabadran, C. Windolf & T. Serre

  5. Complementary surrounds explain diversity of contextual phenomena across visual modalities*

    Psychological Review

    D.A. Mely, D. Linsley & T. Serre

  6. Neural computing on a raspberry pi: Applications to zebrafish behavior monitoring*

    Visual observation and analysis of Vertebrate And Insect Behavior (VAIB)

    L. Govindarajan, T. Sharma, R. Colwill & T. Serre

  7. Not-So-CLEVR: learning same–different relations strains feedforward neural networks

    Royal Society Interface Focus

    J.K Kim, M. Ricci & T. Serre

  8. Same-different problems strain convolutional neural networks

    Annual Meeting of the Cognitive Science Society

    M. Ricci, J.K. Kim & T. Serre

  9. TDP-43 gains function due to perturbed auto-regulation in a Tardbp knock-in mouse model of ALS-FTD

    Nature Neuroscience

    M.A. White et al

  10. Learning to predict action potentials end-to-end from calcium imaging data

    IEEE Conference on Information Sciences and Systems

    D Linsley, J Linsley, T Sharma, N Meyers & T Serre

    2017

  1. What are the visual features underlying human versus machine vision?

    IEEE ICCV Workshop on the Mutual Benefit of Cognitive and Computer Vision

    D Linsley, S Eberhardt, T Sharma, P Gupta & T Serre

    2016

  1. Models of visual categorization

    Wiley Interdisciplinary Reviews: Cognitive Science

    T. Serre

  2. How deep is the feature analysis underlying rapid visual categorization?

    Neural Information Processing Systems

    S. Eberhardt, J. Cader & T. Serre

  3. Computer vision cracks the leaf code

    Proceedings of the National Academy of Sciences

    P. Wilf, S. Zhang, S. Chikkerur, S. Little, S. Wing & T. Serre

  4. Fast ventral stream neural activity enables rapid visual categorization

    Neuroimage

    M. Cauchoix*, S.M. Crouzet*, D. Fize & T. Serre

  5. Source modelling of ElectroCorticoGraphy (ECoG) data: Analysis of stability and spatial filtering

    Journal of Neuroscience Methods

    A. Pascarella, C. Todaro, M. Clerc, T. Serre and M. Piana

  6. Towards a theory of computation in the visual cortex

    Computational and Cognitive Neuroscience of Vision

    D. Mely & T. Serre

  7. An end-to-end generative framework for video segmentation and recognition

    IEEE Winter conference on Applications of Computer Vision

    H. Kuehne, J. Galle & T. Serre

  8. A systematic comparison between visual cues for boundary detection

    Vision Research (Special Issue on Vision and the Statistics of the Natural Environment)

    D.A. Mély, J. Kim, M. McGill, Y. Guo and T. Serre

    2015

  1. Explaining the timing of natural scene understanding with a computational model of perceptual categorization

    PLoS Computational Biology

    I. Sofer, S. Crouzet & T. Serre

  2. Unsupervised invariance learning of transformation sequences in a model of object recognition yields selectivity for non-accidental properties

    Frontiers in Computational Neuroscience

    S.M. Parker & T. Serre

  3. Reduced expression of MYC increases longevity and enhances healthspan

    Cell

    J.W. Hofmann et al

    2014

  1. The neural dynamics of face detection in the wild revealed by MVPA

    Journal of Neuroscience

    M. Cauchoix^, G. Barragan-­Jason^, T. Serre* & E.J. Barbeau* (^,* are authors with equal contributions)

  2. Neuronal synchrony in complex-valued deep networks

    International Conference on Learning Representations

    D. Reichert & T. Serre

  3. The language of actions: Recovering the syntax and semantics of goal-directed human activities

    IEEE Conference on Computer Vision and Pattern Recognition

    H. Kuehne, A. Arlsan & T. Serre

  4. Hierarchical models of the visual system

    Encyclopedia of Computational Neuroscience

    T. Serre

  5. Learning sparse prototypes for crowd perception via ensemble coding mechanisms

    5th International Workshop on Human Behavior Understanding

    Y. Zhang, S. Zhang, Q. Huang & T. Serre

    2013

  1. Neural representation of action sequences: How far can a simple snippet-matching model take us?

    Neural Information Processing Systems

    C. Tan, J. Singer, T. Serre, D. Sheinberg & T. Poggio

  2. Models of the visual cortex

    Scholarpedia, 8(4):3516.

    T. Poggio & T. Serre

    2012

  1. The ankyrin 3 (ANK3) bipolar disorder gene regulates mood-related behaviors that are modulated by lithium and stress*

    Biological Psychiatry

    M. Leussis, E. Berry-Scott, M. Saito, H. Jhuang, G. Haan, O. Alkan, C. Luce, J. Madison, P. Sklar, T. Serre, D. Root, T. Petryshen

  2. A new biologically inspired color image descriptor

    Proceedings of the European Computer Vision Conference

    J. Zhang, Y. Barhomi, T. Serre

  3. The neural dynamics of visual processing in monkey extrastriate cortex: A comparison between univariate and multivariate techniques

    Neural Information Processing Systems – Workshop on Machine Learning and Interpretation in Neuroimaging

    M. Cauchoix, A. Arslan, D. Fize, T. Serre

    2011

  1. What are the visual features underlying rapid recognition?

    Frontiers in Psychology

    S.M. Crouzet & T. Serre

  2. Object decoding with attention in inferior temporal cortex

    Proceedings of the National Academy of Sciences

    Y. Zhang*, E. Meyers*, N. Bichot, T. Serre, T. Poggio, R. Desimone

  3. HMDB: A large video database for human motion recognition

    IEEE International Computer Vision Conference

    H. Kuhne, H. Jhuang, E. Garrote, T. Poggio, T. Serre

    2010

  1. Automated home-cage behavioral phenotyping of mice

    Nature Communications

    H. Jhuang, E. Garrote, X. Yu, V. Khilnani, T. Poggio, A. Steele, T. Serre

  2. What and where: A Bayesian inference theory of attention

    Vision Research

    S. Chikkerur, T. Serre, C. Tan, T. Poggio

  3. Elements for a neural theory of the processing of dynamic faces

    Dynamic Faces: Insights from Experiments and Computation

    T. Serre, M. Giese

  4. Reading the mind’s eye: Decoding category information during mental imagery

    NeuroImage

    L. Reddy, N. Tsuchyia, T. Serre

  5. The story of a single cell: Peeking into the semantics of spikes

    IAPR Workshop on Cognitive Information Processing

    R. Kliper, T. Serre, D. Weinshall, I. Nelken

  6. A neuromorphic approach to computer vision

    Communications of the ACM

    T. Serre & T. Poggio

    2009

  1. Attentive processing improves object recognition

    MIT Computer Science and Artificial Intelligence Laboratory Technical Report

    S. Chikkerur, T. Serre, T. Poggio

  2. A Bayesian inference theory of attention: neuroscience and algorithms

    MIT Computer Science and Artificial Intelligence Laboratory Technical Report

    S. Chikkerur, T. Serre, T. Poggio

    2007

  1. Robust object recognition with cortex-like mechanisms

    IEEE Transactions on Pattern Analysis and Machine Intelligence

    T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber & T. Poggio

  2. A feedforward architecture accounts for rapid categorization*

    Proceedings of the National Academy of Science

    T. Serre, A. Oliva, T. Poggio

  3. A quantitative theory of immediate visual recognition

    Progress in Brain Research, Computational Neuroscience: Theoretical Insights into Brain Function

    T. Serre, G. Kreiman, M. Kouh, C. Cadieu, U. Knoblich, T. Poggio

  4. Learning complex cell invariance from natural videos: a plausibility proof

    MIT Computer Science and Artificial Intelligence Laboratory Technical Report

    T. Masquelier, T. Serre, S. Thorpe, T. Poggio

  5. A biologically inspired system for action recognition

    Proceedings of the Eleventh IEEE International Conference on Computer Vision

    H. Jhuang, T. Serre, L. Wolf, T. Poggio

  6. A component-based framework for face detection and identification

    International Journal of Computer Vision

    B. Heisele, T. Serre, T. Poggio

    2006

  1. Learning a dictionary of shape-components in visual cortex: Comparison with neurons, humans and machines

    MIT Computer Science and Artificial Intelligence Laboratory Technical Report

    T. Serre

    2005

  1. A theory of object recognition: computations and circuits in the feedforward path of the ventral stream in primate visual cortex

    MIT Computer Science and Artificial Intelligence Laboratory

    T. Serre, M. Kouh, C. Cadieu, U. Knoblich, G. Kreiman, T. Poggio

  2. Learning features of intermediate complexity for the recognition of biological motion

    ICANN 2005

    R. Sigala, T. Serre, T. Poggio, M. Giese

  3. Object recognition with features inspired by visual cortex

    IEEE Computer Vision and Pattern Recognition Conference

    T. Serre, L. Wolf, T. Poggio

  4. Error weighted classifier combination for multi-modal human identification

    MIT Computer Science and Artificial Intelligence Laboratory Technical Report

    Y. Ivanov, T. Serre, J. Bouvrie

    2004

  1. Realistic modeling of simple and complex cell tuning in the HMAX model, and implications for invariant object recognition in cortex

    MIT Computer Science and Artificial Intelligence Laboratory

    T. Serre, M. Riesenhuber

  2. A new biologically motivated framework for robust object recognition

    MIT Computer Science and Artificial Intelligence Laboratory

    T. Serre, L. Wolf, T. Poggio

  3. Using component features for face recognition

    International Conference on Automatic Face and Gesture Recognition

    Y. Ivanov, B. Heisele, T. Serre

    2003

  1. Hierarchical classification and feature reduction for fast face detection with support vector machines

    Pattern Recognition

    B. Heisele, T. Serre, S. Prentice, T. Poggio

    2002

  1. On the role of object-specific features for real-world object recognition in biological vision

    Workshop on Biologically Motivated Computer Vision

    T. Serre, J. Louie, M. Riesenhuber, T. Poggio

  2. Categorization by learning and combining object parts

    Advances in Neural Information Processing Systems

    B. Heisele, T. Serre, M. Pontil, T. Vetter, T. Poggio

    2001

  1. Feature reduction and hierarchy of classifiers for fast object detection in video images

    Computer Vision and Pattern Recognition

    B. Heisele, T. Serre, S. Mukherjee, T. Poggio

  2. Component-based face detection

    Computer Vision and Pattern Recognition

    B. Heisele, T. Serre, M. Pontil, T. Poggio

    2000

  1. Feature selection for face detection

    MIT Center for Biological and Computational Learning

    T. Serre, B. Heisele, S. Mukherjee, T. Poggio

    Year
  1. Work in progress
  2. 2023
  3. 2022
  4. 2021
  5. 2020
  6. 2019
  7. 2018
  8. 2017
  9. 2016
  10. 2015
  11. 2014
  12. 2013
  13. 2012
  14. 2011
  15. 2010
  16. 2009
  17. 2007
  18. 2006
  19. 2005
  20. 2004
  21. 2003
  22. 2002
  23. 2001
  24. 2000
  25. Google Scholar Citations