We're starting the year off with a series of talks on recent advances in Deep Learning. The researchers presenting their work are PhDs and post-docs in machine learning under the supervision of prof. Max Welling, who also acts as VP of Technology at Qualcomm.
All talks will be 20-25 minutes with 5-10 minutes for questions.
15:00 - 15:30 Rianne van de Berg
Improving VAEs with Sylvester and Sinkhorn transformations
15:30 - 16:00 Wouter Kool
Deep Reinforcement Learning for Logistics Problems
16:00-16:30 Thomas Kipf:
Neural Relational Inference with Graph Neural Networks
16:30-17:00 Daniel Worrall:
Scale and other Symmetries in Deep learning
Rianne van de Berg received her PhD in theoretical condensed matter physics in 2016 at the University of Amsterdam. She is currently a postdoctoral researcher in machine learning at the University of Amsterdam. She has worked on deep learning for graph structured data, and the present focus of her research is on generative modelling.
Wouter Kool is Operations Research Engineer at ORTEC and PhD candidate at the Amsterdam Machine Learning Lab (AMLab). His research focuses on using (Deep) Reinforcement Learning to learn algorithms capable of solving practical (combinatorial) optimization problems.
Thomas Kipf is a third-year PhD student at the University of Amsterdam. His research focuses on deep learning with (graph-)structured representations, including topics such as semi-supervised learning, multi-agent modeling, and structured deep generative models.
Daniel Worrall is a postdoctoral researcher working at the University of Amsterdam, in the Philips Laboratory. He is interested in equivariant neural networks, approximate Bayesian inference, uncertainty quantification, and medical imaging. He read Information Engineering at the University of Cambridge (BA, MEng) and Computer Vision at University College London (PhD), where he was briefly involved with Amnesty International’s Decoders Unit working on AI for Good.