Geometric deep learning

Speaker:  Michael Bronstein – Lugano, Switzerland
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Abstract

In recent years, more and more data science applications have to deal with a somewhat unusual kind of data residing on non-Euclidean geometric domains such as manifolds or graphs. For instance, in social networks, the characteristics of users can be modeled as signals on the vertices of the social graph. Sensor networks are graph models of distributed interconnected sensors, whose readings are modeled as time-dependent signals on the vertices. In genetics, gene expression data are modeled as signals defined on the regulatory network. In computer graphics and vision, 3D objects are modeled as Riemannian manifolds (surfaces) endowed with properties such as color texture. Furthermore, modeling high-dimensional data with graphs is an increasingly popular trend in general data science, where graphs are used to describe the low-dimensional intrinsic structure of the data. 
The complexity of geometric data and the availability of very large datasets (in the case of social networks, of the billion-scale) make it tempting and very desirable to resort to machine learning techniques. Yet, currently available learning methods have been developed primarily for Euclidean data and are not suitable for the non-Euclidean setting. In this talk, I will overview the emerging field of deep learning on geometric data and show examples of applications from network analysis and computer vision and graphics. 

About this Lecture

Number of Slides:  50
Duration:  45 minutes
Languages Available:  English, Hebrew, Italian, Russian
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.