Graph Representation Learning: Recent Advances and Open Challenges
Speaker: William Hamilton, McGill University and MILA Title: Graph Representation Learning: Recent Advances and Open Challenges Abstract: Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial if we want systems that can learn, reason, and generalize from this kind of […]
CMSA Math-Science Literature Lecture: Hodge structures and the topology of algebraic varieties
Claire Voisin (Collège de France) Title: Hodge structures and the topology of algebraic varieties Abstract: We review the major progress made since the 50’s in our understanding of the topology of complex algebraic varieties. Most of the results we will discuss rely on Hodge theory, which has some analytic aspects giving the Hodge and Lefschetz decompositions, and […]
Self-induced regularization from linear regression to neural networks
https://youtu.be/bjRqmlI_SFs Speaker: Andrea Montanari, Departments of Electrical Engineering and Statistics, Stanford Title: Self-induced regularization from linear regression to neural networks Abstract: Modern machine learning methods --most noticeably multi-layer neural networks-- require to fit highly non-linear models comprising tens of thousands to millions of parameters. Despite this, little attention is paid to the regularization mechanism to […]
CMSA Math-Science Literature Lecture: Area-minimizing integral currents and their regularity
Camillo De Lellis (IAS) Title: Area-minimizing integral currents and their regularity Abstract: Caccioppoli sets and integral currents (their generalization in higher codimension) were introduced in the late fifties and early sixties to give a general geometric approach to the existence of area-minimizing oriented surfaces spanning a given contour. These concepts started a whole new subject which has […]
CMSA Math-Science Literature Lecture: From Deep Learning to Deep Understanding
Harry Shum (Tsinghua University) Title: From Deep Learning to Deep Understanding Abstract: In this talk I will discuss a couple of research directions for robust AI beyond deep neural networks. The first is the need to understand what we are learning, by shifting the focus from targeting effects to understanding causes. The second is the need for a […]