The course covers foundations and recent advances in Machine Learning with emphasis on high dimensional data and a core set techniques, namely regularization methods. In many respects the course is compressed version of the9.520course on Machine Learning atMIT.The course is free of charge, but participants will have to cover their own accommodation and travel.
Progress in artificial intelligence
Recent advances in artificial intelligence were considered out of reach for decades. Modern smart phones recognise voice commands, cameras recognise faces, andcar computers can detect pedestrians and predict collisions. At the root of these advances lie machine learning algorithms,software that learns how to solve a task rather than being explicitly programmed to do so.
Among the variety of approaches to modern computational learning, this course will focus on regularization techniques, that are key to high-dimensional learning. Regularization methods allow to treat in a unified way a huge class of diverse approaches, while providing tools to design new ones. Starting from classical notions of smoothness, shrinkage and margin, the course will cover state of the art techniques based on the concepts of geometry (aka manifold learning), sparsity and a variety of algorithms for supervised learning, feature selection, structured prediction, multitask learning and model selection. Practical applications for high dimensional problems, in particular in computational vision, will be discussed. The classes will focus on algorithmic and methodological aspects, while trying to give an idea of the underlying theoretical underpinnings. Practical laboratory sessions will give the opportunity to have hands on experience.
Dr. Lorenzo Rosasco leads the Laboratory for Computational and Statistical Learning, a joint machine learning laboratory between the Istituto Italiano di Tecnologia (IIT) and the Massachusetts Institute of Technology (MIT). He is associate professor at the University of Genova and a visiting professor at the MIT. He received his PhD from the University of Genova in 2006 and has been visiting student at the Toyota Technological Institute at Chicago and at the Center for Biological and Computational Learning at MIT. He held a research scientist position at MIT between 2006 and 2009, working together with Tomaso Poggio.
His research focuses on studying theory and algorithms for machine learning. Dr. Rosasco has developed and analyzed methods to learn from small as well as large samples of high dimensional data. He is known for his foundational work in machine learning as well as the development of sound machine learning algorithms, based on spectral methods and convex optimization.
Dr. Valeriya Naumova is Deputy Section Director and the Project Manager of the RCN-funded project Function-driven Data Learning in High Dimension.She received her PhD from the Johann Radon Institute for Computational and Applied Mathematics, Austrian Academy of Sciences in 2012 and began work at Simulain the Scientific Computing Department in 2014. Her research focuses on the development of theoretical approaches and numerical methods for learning from samples of complex high-dimensional data sets that are typically noisy, random, and incomplete. She pursues these questions by building upon concepts and techniques primarily from theory of inverse and ill-posed problems, regularization and learning theory, sparse recovery, and compressed sensing.
When: May 02-06 2017
Where: Simula Research Laboratory, Martin Linges vei 25, 1364, Fornebu, Norway (25 minutes away from Oslo city Center)
Sign up at the Reg ML '17 pages, where accommodation details are also available