1 PhD position and 1 Postdoctoral researcher in Machine Learning & Deep Learning
The Informatics Institute is one of the large research institutes of the Faculty of Science with a focus on complex information systems divided in two broad themes: 'Computational Systems' and 'Intelligent Systems.' The institute has a prominent international standing and is active in a dynamic scientific area, with a strong innovative character and an extensive portfolio of externally funded projects.
World-class research groups directly involved in deep learning are AMLAB (machine learning led by Prof. Max Welling), ISIS (computer vision led by Prof. Cees Snoek), and ILPS (information retrieval led by Prof. Maarten de Rijke). Examples of industry funded research labs involved in deep learning are Qualcomm-UVA (QUVA) Lab (12 PhDs/Postdocs), Bosch-UvA DELTA Lab (10 PhDs/Postdocs), Philips Lab (4 PhD/Postdocs) and SAP-UvA Lab (3 PhDs/Postdocs). We also have ongoing collaborations with Microsoft Research (2PhDs).
Bosch, a multinational engineering and electronics company, and the University of Amsterdam, a world-leading computer science department, have started a joint research lab in Amsterdam, the Netherlands, to join the best of academic and industrial research. The lab focuses on fundamental research in deep learning with applications to intelligent vehicles. It hosts 10 PhD and Postdoc research positions and is led by Prof. Max Welling (machine learning), Prof. Arnold Smeulders (computer vision) and Dr Zenep Akata (deep learning). One of the perks of the program is an exchange program where each lab member will stay for one month per year at Bosch Research in Germany.
We are looking for one PhD candidate and one postdoctoral researcher to perform cutting edge research in AMLAB in the field of machine learning.
One of the research topics is 'Methods for Robust Feature Learning' where the goals are to learn features that are robust or invariant to changing conditions, to learn classifiers that perform well on multiple domains, to learn representations that can be transferred between domains and to learn classifiers that do not suffer from adversarial examples.
Keywords: Bayesian Regularization, Model Uncertainty, Domain Transfer, Representation Learning
The second research topic is 'Combining Generative Probabilistic Models with Deep Learning' where the goals are to combine generative models with discriminative deep learning models, to inject expert knowledge into the modeling process, to improve the performance of deep learning using simulator models, to improve deep learning in the small data regime.
Keywords: Variational Autoencoders, Generative Adversarial Networks, Representation Learning
- Master's degree in Artificial Intelligence, Computer Science, Physics or related field;
- excellent programming skills (e.g. C++, Python; Tensorflow, Pytorch or equivalent);
- solid mathematics foundations, especially statistics, calculus and linear algebra;
- highly motivated;
- fluent in English, both written and spoken.
Proven experience with machine learning / computer vision is a big plus.
For more information click "LINK TO ORIGINAL" below.