Pol Comellas
Research Scientist at DeepMind
London, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolPol Comellas is a research scientist at DeepMind with 11 years of experience bridging machine learning and computer vision, building generative models that combine object shape, appearance and rendering with deep learning for interpretable scene understanding. He completed an MSc and PhD in Artificial Intelligence at the University of Edinburgh under Chris Williams and previously interned at DeepMind, blending academic rigor with industry-scale research. Pol’s work focuses on marrying generative and discriminative approaches to produce both accurate and explainable image representations, a perspective that helps close the gap between probabilistic modeling and modern deep nets. Based in London, he brings a strong European engineering foundation from Universitat Pompeu Fabra and a track record of translating principled generative ideas into practical deep learning systems.
11 years of coding experience
Master's degree, Artificial Intelligence, Master's degree, Artificial Intelligence at The University of EdinburghUniversitat Pompeu FabraBachelor's degree, Ingeniería informática, Bachelor's degree, Ingeniería informática at Universitat Pompeu Fabra - Barcelona
Github Skills (9)
python9
statistics9
machine-learning8
data-analysis8
data-science8
glm8
opengl8
scikit7
scikit-learn7
Programming languages (2)
Github contributions (4)
polmorenoc/inversegraphics
Mar 2015 - Mar 2018
Contributions:284 commits, 48 pushes, 1 branch in 3 years
polmorenoc/opendr
Jul 2015 - Apr 2019
Modern OpenDR
Contributions:136 commits, 77 pushes, 2 comments in 3 years 9 months
openglglm
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.