Guillaume Alain
Deep Learning Researcher at Mila - Quebec Artificial Intelligence Institute
Montreal, Quebec, Canada
Summary
👤
Senior🎓
Top SchoolGuillaume Alain is a Deep Learning Researcher based in Montreal with 14 years of software and research experience and a PhD in Deep Learning from Université de Montréal under Yoshua Bengio. He has bridged low-level systems and cutting-edge ML research, contributing CUDA/FFT convolution support to Theano and modernizing classic DeepLearningTutorials for Python 3. At Mila he focuses on deep and reinforcement learning and is branching into AI-driven music generation, combining mathematical rigour from earlier number theory work with practical engineering. His background includes production-grade QA and performance tooling at Solace and applied optimization for radio coverage analysis, giving him a strong applied sense for robust systems. Known for hands-on problem solving, he uniquely pairs deep theoretical training with GPU-optimized implementation experience.
14 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD, Deep Learning, Doctor of Philosophy - PhD, Deep Learning at Université de MontréalM.Sc, Computer Science, M.Sc, Computer Science at The University of British ColumbiaMaster's, Mathematics (Number Theory), Master's, Mathematics (Number Theory) at University of Ottawa
French, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (14)
cuda10
fftw10
convolution10
gpu-programming10
machine-learning10
fft10
deep-learning10
python10
theano10
testing9
n9
rnn-model9
lstm9
numpy8
Programming languages (2)
Github contributions (5)
Theano/Theano
May 2014 - Jun 2015
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:
ML Engineer
ML EngineerContributions:11 commits, 5 PRs, 5 comments in 1 year 1 month
Contributions summary:Guillaume focused on implementing and testing FFT-based convolution operations within the Theano library, specifically for CUDA-enabled GPUs. Their contributions included adding 3D convolution support, expanding existing 2D convolution functionality, and addressing edge cases related to input padding. The user implemented unit tests to validate the correctness of the FFT convolution operations. Their work primarily involved modifying and extending existing CUDA code for optimized convolution calculations.
python-librarymathmulti-dimensionalpythonevaluate
lisa-lab/DeepLearningTutorials
Jan 2016 - Feb 2016
Deep Learning Tutorial notes and code. See the wiki for more info.
Role in this project:ML Engineer
ML EngineerContributions:9 commits, 1 PR, 7 comments in 19 days
Contributions summary:Guillaume primarily focused on porting and fixing deep learning tutorial code, addressing compatibility issues with Python 3. Their contributions included fixing and testing code for various models such as LSTM, SdA, DBN, RBM, and RNN-RBM, and making adjustments to accommodate Python 3 compatibility. Specific adjustments were made to the rnnslu.py and rnnrbm.py files. The user also made adjustments to the code to remove uses of `xrange` and replaced them with the correct alternative in Python 3.
notesdeep-learningmachinelearningmore-infomachine-learning
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.