Nicolas Ballas
Research Scientist At FAIR (Facebook AI Research)
France
Summary
🤩
Rockstar🎓
Top SchoolNicolas Ballas is a research scientist at FAIR with 12 years of experience bridging academic rigor and production-grade machine learning, specializing in image and video processing. He holds a PhD from Mines ParisTech and completed postdoctoral work at MILA, with a Fulbright-supported stint at CMU focused on event and action recognition in large video datasets. His background spans industry R&D—from medical imaging at Siemens to large-scale image retrieval at LTU—and contributions to open-source ML tooling, notably optimizing Theano's 3D convolution kernels and FFT-based GPU ops. Fluent in French and English, he codes in C++, Python and Ruby and combines strong applied math foundations with practical systems know-how. An uncommon detail: he has repeatedly moved between academic research and hands-on engineering roles, making him adept at turning complex research ideas into performant implementations.
11 years of coding experience
6 years of employment as a software developer
Master, Machine learning and Computer vision, Master, Machine learning and Computer vision at Ecole normale supérieurePhD, Applied Mathematics, Computer Science, PhD, Applied Mathematics, Computer Science at Mines Paris - PSLMaster, Computer Science, Master, Computer Science at EPITA: Ecole d'Ingénieurs en Informatique
French, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (11)
neural-network10
convolutional-neural-networks10
gpu10
cudnn10
optimisation10
python10
theano10
optimization10
fft9
machine-learning9
fourier-transform9
Programming languages (1)
Github contributions (5)
Theano/Theano
Jul 2014 - Feb 2017
Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor
Role in this project:
Backend Developer & ML Engineer
Backend Developer & ML EngineerContributions:147 commits, 20 PRs, 6 pushes in 2 years 7 months
Contributions summary:Nicolas's commits primarily focus on optimizing the Theano library, specifically within the context of 3D convolutional operations. Their contributions involve implementing and refining FFT-based optimizations for GpuConv3D, GpuConvGrad3D, and GpuConvTransp3D. They added stride value checks and addressed padding issues. The user also moved intermediate 3DFFT functions within the opt and added tests for optimization, adding a new batch normalization op.
python-librarymathmulti-dimensionalpythonevaluate
ballasn/Theano
Jan 2015 - Aug 2016
Contributions:5 PRs, 67 pushes, 20 branches in 1 year 7 months
matharraypythonmeta-programminggpu
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.