Robert Peharz
Department / Institute
Group

RESEARCH PROFILE
Robert Peharz is an Assistant Professor in the Artificial Intelligence cluster at Eindhoven University of Technology. Robert's work leverages probability as a principled language to represent and process uncertain knowledge. His main research activity is dedicated to develop powerful and expressive machine learning algorithms which are based on probabilistic principles. His particular research targets are probabilistic graphical models, tractable probabilistic models such as probabilistic circuits, and probabilistic deep learning. In his work, Robert aims to unite principled probabilistic modeling with the power of the entire machine learning toolbox.
Uncertainty Matters
ACADEMIC BACKGROUND
Robert Peharz received his Master degree in Computer Engineering from Graz University of Technology (TU Graz), Austria (2010). From 2010-2015, he pursued his PhD studies at TU Graz, working on probabilistic graphcial models and sum-product networks, with applications to signal processing. From 2015-2017, he was postdoc at the Medical University of Graz, working on interdisciplinary approaches for early recognition of neural maldevelopment via behavioral neuroscience. He was postdoc in the Machine Learning Group (MLG) at the University of Cambridge from 2017-2018. He was Marie-Curie Individual Fellow at MLG Cambridge from 2018-2019. Robert joined Eindhoven University of Technology (TU/e) in November 2019 as an Assistant Professor in the Artificial Intelligence cluster.
Recent Publications
-
PS3
2020 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2020) (2021) -
Towards Robust Classification with Deep Generative Forests
37th International Conference on Machine Learning (ICML 2020) (2020) -
Deep Structured Mixtures of Gaussian Processes
23rd International Conference on Artificial Intelligence and Statistics, ONLINE (2020) -
Joints in Random Forests
(2020) -
Joints in Random Forests
Conference on Neural Information Processing Systems (2020)
Ancillary Activities
No ancillary activities