Robert Peharz

Associate Professor

Graz, Styria, Austria
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Robert Peharz is an Associate Professor and machine learning researcher with a decade of experience specializing in probabilistic ML, tractable inference, causality, and physics-informed and neurosymbolic learning. He has held academic posts across Europe, including Marie-Curie fellowship at Cambridge, assistant professorships at TU Eindhoven and TU Graz, and a postdoc at Medical University Graz, blending theoretical advances with applied experimental design and Bayesian optimization. His work focuses on making inference both expressive and tractable, and he actively explores active learning and experimental design to close the loop between data acquisition and model uncertainty. Based in Graz, Austria, he combines deep probabilistic expertise with a background in telematics and a knack for translating interdisciplinary problems—especially at the intersection of physics and ML—into practical, scalable methods.
code11 years of coding experience
job2 years of employment as a software developer
bookDoctor of Philosophy - PhD, Machine Learning, Doctor of Philosophy - PhD, Machine Learning at Technische Universität Graz
github-logo-circle

Github Skills (10)

deep-learning8
machine-learning8
python8
tensorflow7
neural-network6
ml5
deep-neural-networks5
pytorch3
numpy2
gaussian-processes2

Programming languages (3)

JuliaC++Python

Github contributions (5)

github-logo-circle
cambridge-mlg/RAT-SPN

Jun 2019 - Jun 2020

Code for UAI'19: Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning
Contributions:5 commits, 11 pushes, 1 branch in 11 months
deep-learning
smatmo/ProjectionOntoSimplex

Aug 2019 - Apr 2024

Simplex projection (numpy, pytorch), from Duchi et al., "Efficient Projections onto the l1-Ball for Learning in High Dimensions", ICML 2008
Contributions:3 pushes, 1 branch in 4 years 8 months
numpypytorch
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.
Request Free Trial