Friday, November 30 2018
12:15pm - 1:15pm
For more information:

Allie McFadden

Communications Officer

Add To My Calendar
Machine Learning Seminar Fall 2018 — Qixing Huang, The University of Texas at Austin

The Machine Learning Center at Georgia Tech presents a seminar by Qixing Huang of The University of Texas at Austin. The event will be held in the Marcus Nanotechnology Building, Rooms 1116-1118, from 12:15-1:15 p.m. and is open to the public.

Talk Title

Map Synchronization: from Object Correspondences to Neural Networks


Maps between geometric objects are deeply interesting. High-quality maps facilitate information propagation and aggregation, leading to numerous applications in geometry reconstruction, synthesis, analysis and prediction. In the deep learning era, the concept of maps naturally generalizes to neural networks between pairs of domains. Despite the importance of maps, map computation remains quite challenging, particularly between dissimilar objects. Map synchronization addresses this challenge by jointly optimizing maps among a collection of relevant objects, which allows us to compute maps between dissimilar objects by composing maps along paths of similar object pairs.

In this talk, we will discuss several recent works on map synchronization: joint map and symmetry synchronization, learning to transformation synchronization and learning a network of neural networks. We will focus on both theoretical connections to optimization, representation theory and graph theory, and practical applications in 3D reconstruction and 3D understanding.


Qixing Huang obtained his PhD in Computer Science from Stanford University in 2012. From 2012 to 2014 he was a postdoctoral research scholar at Stanford University. From 2014 to 2016 he was a research assistant professor at Toyota Technological Institue at Chicago. He received his MS and BS in Computer Science from Tsinghua University. He has also interned at Google Street View, Google Research and Adobe Research. His research spans computer vision, computer graphics, computational biology and machine learning. In particular, his recent focus is on developing machine learning algorithms (particularly deep learning) that leverage Big Data to solve core problems in computer vision, computer graphics and computational biology. He is also interested in statistical data analysis, compressive sensing, low-rank matrix recovery, and large-scale optimization, which provide theoretical foundation for much of his research.


RSVP here by Tuesday, November 27th

Click images in enlarge.