Siamak Mehrkanoon
Assistant Professor at Utrecht University
Leuven, Flemish Brabant, Belgium
Summary
👤
Senior🎓
Top SchoolSiamak Mehrkanoon is an assistant professor and machine learning researcher with eight years of academic and industry experience developing deep learning, domain adaptation, and semi‑supervised models for image, video and signal processing. He combines a strong numerical-analysis background (PhD work and earlier HPC MPI implementations for ODE simulation) with practical data‑driven modeling and predictive analytics, enabling robust parameter estimation for dynamical systems. His trajectory includes postdoctoral and research fellowships across KU Leuven, University of Waterloo, Tübingen and Maastricht, and he currently holds a faculty position at Utrecht University. Siamak has a track record of scaling semi‑supervised approaches to millions of partially labeled examples and applying transfer learning to cross‑modal tasks like image‑text and action recognition. Beyond publications and teaching, he has repeatedly secured competitive research funding and international visiting grants, reflecting both scientific rigor and collaborative reach.
8 years of coding experience
10 years of employment as a software developer
Doctor of Philosophy (PhD), Machine Learning, Doctor of Philosophy (PhD), Machine Learning at Katholieke Universiteit LeuvenDoctor of Philosophy (Ph.D.), Numerical Analysis, Doctor of Philosophy (Ph.D.), Numerical Analysis at Universiti Putra Malaysia
Persian, English, Dutch
Github Skills (1)
convolutional-neural-networks10
Programming languages (1)
Github contributions (5)
HansBambel/SmaAt-UNet
Jul 2020 - Jul 2022
PyTorch-Code for the Paper "SmaAt-UNet: Precipitation Nowcasting using a Small, Attentive UNet-Architecture"
Contributions:4 commits, 4 pushes in 2 years
convolutional-neural-networksprecipitation-nowcastingunetunet-pytorchweather-forecast
SMehrkanoon/Deep-brain-state-classification-of-MEG-data
Jun 2020 - Jul 2020
Contributions:15 commits, 1 push in 8 days
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.