About me

I am a postdoc at UC Berkeley in the Gallant Lab. I defended my Ph.D. in 2018, in the Image, Data, Signal department at Telecom ParisTech in France, supervised by Alexandre Gramfort and Yves Grenier. I graduated from Ecole polytechnique in 2013 and EPFL in 2015.

My work focuses on signal processing and machine learning for neuroscience.

I am also a core developer of scikit-learn since 2015.

News

Blog posts

Publications

2019

Laetitia Grabot, Tadeusz W. Kononowicz, Tom Dupré la Tour, Alexandre Gramfort, Valérie Doyère, Virginie van Wassenhove
Journal of Neuroscience, 2019
[pdf] [ bibtex]

2018

Tom Dupré la Tour
PhD Thesis, 2018
[pdf] [ book_pdf] [ tel] [ pastel] [ bibtex] [ slides] [ video]
Tom Dupré la Tour*, Thomas Moreau*, Mainak Jas, Alexandre Gramfort
NeurIPS, 2018
[pdf] [ arxiv] [ bibtex] [ poster] [ code]
Tom Dupré la Tour, Yves Grenier, Alexandre Gramfort
ICASSP, 2018
[pdf] [ bibtex] [ poster]

2017

Tom Dupré la Tour, Lucille Tallot, Laetitia Grabot, Valérie Doyere, Virginie van Wassenhove, Yves Grenier, Alexandre Gramfort
PLOS Computational biology, 2017
[pdf] [ biorxiv] [ bibtex] [ poster] [ slides] [ code]
Mainak Jas, Tom Dupré la Tour, Umut Şimşekli, Alexandre Gramfort
NeurIPS, 2017
[pdf] [ arxiv] [ bibtex] [ poster] [ code]
Tom Dupré la Tour, Yves Grenier, Alexandre Gramfort
ICASSP, 2017
[pdf] [ bibtex] [ poster] [ code]

Talks

2018

Tom Dupré la Tour
PhD defense, 2018
[slides] [ video]
Tom Dupré la Tour
PyParis, 2018
[slides] [ video]
Tom Dupré la Tour
PyData Paris meetup, 2018
[slides]

2017

Tom Dupré la Tour, Lucille Tallot, Laetitia Grabot, Valérie Doyere, Virginie van Wassenhove, Yves Grenier, Alexandre Gramfort
Coupling and Causality in Complex Systems (C3S), 2017
[slides]
Tom Dupré la Tour, Lucille Tallot, Laetitia Grabot, Valérie Doyere, Virginie van Wassenhove, Yves Grenier, Alexandre Gramfort
Organization for Human Brain Mapping (OHBM) annual meeting, 2017
[poster]
Tom Dupré la Tour, Yves Grenier, Alexandre Gramfort
International Biomedical and Astronomical Signal Processing (BASP) Frontiers workshop, 2017
[poster]

2016

Tom Dupré la Tour
PyParis 2016
[slides]

Software

Machine Learning in Python - Core developer
Implementation of optimization algorithms (SAG, cd-NMF, mu-NMF), library maintenance.

Phase amplitude coupling (PAC) in Python - Main developer
Estimation of PAC in neural time series. In particular, it implements driven auto-regressive (DAR) models.

Convolutional dictionary learning for noisy signals using αCSC in Python - Core developer
αCSC is a model of convolutional sparse coding with an α-stable distribution to handle heavy-tailed noise.

Experience

2019-????

(current)
Postdoc at UC Berkeley
Research in Machine Learning for fMRI Neuroimaging
in Jack Gallant's lab (Hellen Wills Neuroscience Institute)

2015-2018

(3 years)
PhD student at Telecom ParisTech
Research in Signal Processing and Machine Learning for Neuroscience
Thesis: Non-linear models for neurophysiological time series.
Advised by Alexandre Gramfort and Yves Grenier
1st PhD student award from STIC doctoral school at Université Paris-Saclay
1st PhD thesis award in Signal, Image and Vision, from the Club EEA, GRETSI and GdR ISIS

2015

(5 months)
Research developer at Telecom ParisTech
Development of scikit-learn, an open source machine learning library in python.
Development of SAG and NMF algorithms, library maintenance.

2014

(6 months)
Research intern at DxO Labs
Image processing research on motion deblurring.
Literature review, prototyping on Matlab, state of the art improvement (not published).

2013

(3 months)
Research on a new calculus paradigm using stochastic binary signals.
Matlab simulations and implementation of these gates with analogic CMOS circuit (with Cadence).
Summa cum laude from Ecole polytechnique (top 10%)

2011

(7 months)
Full time first responder at Paris Fire Brigade
Lead a first aiders unit at Paris Fire Brigade.
Decision making in critical situations (childbirth, cardiac arrests, ...)

Teaching

2016-2017

Practical datascience
One-week data camp - Université Paris-Saclay (M2)

Linear time series
SIGMA202a - Télécom ParisTech (M1)

Advisor for a year-long innovative team project
PACT - Télécom ParisTech (L3)

Education

2015-2018

Télécom ParisTech - PhD in Signal Processing for Neuroscience
Thesis: Non-linear models for neurophysiological time series.
Advised by Alexandre Gramfort and Yves Grenier

2013-2015

EPFL - Master in Information Technology
Signal Processing, Image Processing, Video compression, Machine Learning, Distributed Information Systems, Wireless Transmission Algorithms, Microwaves, Photonics.
Research project on Human Echolocation.

2010-2013

Ecole polytechnique - Engineer degree (Master)
1st et 2nd years : cross-curricular formation, with Mathematics, Physics and Informatics.
3rd year : specialization in Electrical Engineering : Computer Architecture, Printed Circuit Board Design, Semiconductor Physics, Photovoltaic, Signal Processing, Opto-Electronic.

2008-2010

CPGE at Lycée Saint Louis - Undergraduate study
A 2-year intensive undergraduate program for admission to France’s top engineering schools.
Mathematics, Physics.