Geometric Deep Learning on Graphs and Manifolds: Going Beyond Euclidean Data // IACS Seminar

Date: 

Friday, January 26, 2018, 12:30pm to 2:00pm

Location: 

Harvard SEAS, Maxwell Dworkin G115, 33 Oxford Street, Cambridge MA 02138

Lunch will be served from 12:30-1pm, on a first-come, first served basis.  The talk will begin at 1pm.

Abstract: In the past decade, deep learning methods have achieved unprecedented performance on a broad range of problems in various fields from computer vision to speech recognition. So far research has mainly focused on developing deep learning methods for Euclidean-structured data. However, many important applications have to deal with non-Euclidean structured data, such as graphs and manifolds. Such data are becoming increasingly important in computer graphics and 3D vision, sensor networks, drug design, biomedicine, high energy physics, recommendation systems, and web applications. The adoption of deep learning in these fields has been lagging behind until recently, primarily since the non-Euclidean nature of objects dealt with makes the very definition of basic operations used in deep networks rather elusive. In this talk, Dr. Bronstein will introduce the emerging field of geometric deep learning on graphs and manifolds, overview existing solutions and applications, and outline the key difficulties and future research directions.

Bio: Michael Bronstein is an associate professor at Università della Svizzera italiana (Switzerland) and Tel Aviv University (Israel). He also serves as a principal engineer at Intel’s perceptual computing group. His main research interests are in theoretical and computational geometric models and their applications to problems from the fields of computer vision, graphics, and machine learning.

At Radcliffe, Bronstein is working on developing formulations of deep learning for non-Euclidean structured data such as graphs and manifolds, which are becoming increasingly important in a variety of fields including computer vision, sensor networks, biomedicine, genomics, and computational social sciences. He hopes that new geometric deep learning paradigms will help achieve quantitatively and qualitatively better results in these fields.

Bronstein received his PhD (summa cum laude) in computer science from the Technion–Israel Institute of Technology. He was awarded three European Research Council grants, a Google Faculty Research Award, and the Rudolf Diesel Industry Fellowship at the Technical University of Munich. He is a member of the Young Academy of Europe and ACM Distinguished Speaker. In 2014, he was named a World Economic Forum Young Scientist. Aside from his academic work, Bronstein is actively involved in the industry and has cofounded and served in technical and management positions at several successful startups, including Invision, which was acquired by Intel in 2012. He was one of the key developers of Intel RealSense technology.

**This event is free and open to the public; no registration required.**

 

See also: Seminar