Organizers

LS is a postdoctoral fellow at EPFL. He obtained his PhD in 2017 at the Courant Institute of Mathematical Sciences, NYU. At NYU and Facebook AI Research, he worked with Gerard Ben Arous, Yann LeCun, and Leon Bottou focusing on the geometry of loss functions in deep learning, as well as applications of machine learning to social sciences. His current work is on understanding the interaction between the architecture, data, and the optimization algorithm in modern deep learning methods. He took reviewing role for conferences and journals such as ICLR, JMLR, COLT, NeurIPS, TPAMI, SIAM Journal, and he also reviewed a book chapter for Cambridge University Press. Home Page, Google Scholar

CG has finished his MSc on Cognitive Science from Middle East Technical University. He earned his PhD from University of Montreal MILA lab under the supervision of Yoshua Bengio. During his PhD, he has worked on a vast number of topics from natural language understanding to optimization and deep learning architectures. He is a research scientist at Deepmind working on core machine learning and reinforcement learning algorithms. CG act as a PC for conferences such as ICML, ICLR, NeurIPS, ICML, ECML/KDD, and reviewer for journals such as JMLR and Neural Computation. Home Page, Google Scholar

AR is a research scientist at Facebook AI Research (FAIR) and an adjunct professor at McGill University. Previously, she was a postdoctoral researcher at Montreal Institute for Learning Algorithms, advised by Prof. Yoshua Bengio. Her postdoctoral research revolved around deep learning techniques to tackle biomedical challenges, such as the ones posed by imaging multi-modality, high dimensional data, and graph-structured data. She received her PhD from the University of Barcelona in 2015. Her thesis was on assisting the training of deep neural networks with applications to computer vision, advised by Dr. Carlo Gatta. Her PhD included contributions in the fields of representation learning and model compression, with applications to image classification, image segmentation, and remote sensing. Home Page, Google Scholar

NR is a Research Scientist at Element AI and her main areas of interest are computer vision and multimodal learning, particularly problems with fewer available labeled data, including but not limited to zero-shot and few-shot learning, domain adaptation, and active learning. She received her PhD from the University of Trento in 2017, and has spent more than 2 years at MILA (Montreal Institute of Learning Algorithms) during her PhD Negar has worked as a research intern at the Multimedia and Vision lab at the Queen Mary University of London and in the Research and Machine Intelligence group at Google. She has been involved in many initiatives to increase diversity and inclusion in the field. Some of these include co-founding and co-organizing the Women in Deep Learning (WiDL) workshop in 2016 and 2017, co-organizing the Women in Machine Learning (WiML) workshop at NeurIPS in 2017, the Women in Computer Vision (WiCV) workshop at CVPR in 2017. Home Page, Google Scholar

NdF is a lead research scientist at DeepMind, and a Fellow of the Canadian Institute For Advanced Research (CIFAR) in the successful Neural Computation and Adaptive Perception program. He received his PhD from Trinity College, Cambridge University in 2000 on Bayesian methods for neural networks. From 1999 to 2001, he was a postdoctoral fellow at UC Berkeley in the AI group of Stuart Russell. He was a professor at the University of British Columbia from 2001 to 2014. He has spun off a few companies, most recently Dark Blue Labs acquired by Google. Among his recent awards are best paper awards at IJCAI 2013, ICLR 2016, ICML 2016, and the Yelp Dataset award for a multi-instance transfer learning paper at KDD 2015. He also received the 2012 Charles A. McDowell Award for Excellence in Research, and the 2010 Mathematics of Information Technology and Complex Systems (MITACS) Young Researcher Award. Home Page, Google Scholar