Moderator: Andrew Glassner, Weta Digital, United States of America
Andrew Glassner is a Senior Research Scientist at Weta Digital, where he combines deep learning and computer graphics. He was Technical Papers Chair for SIGGRAPH '94, Founding Editor of the Journal of Computer Graphics Tools, and Editor-in-Chief of ACM Transactions on Graphics. Glassner's many books include the "Graphics Gems" series, the textbook "Principles of Digital Image Synthesis," and the "Andrew Glassner's Notebook" series. His most recent book is "Deep Learning: From Basics to Practice." Glassner has written 3 novels, and directed both film and online entertainment. He holds a PhD from UNC-Chapel Hill. He paints, plays jazz piano, and hikes.

Lecturer(s): Andrew Glassner, Weta Digital, United States of America
Andrew Glassner is a Senior Research Scientist at Weta Digital, where he combines deep learning and computer graphics. He was Technical Papers Chair for SIGGRAPH '94, Founding Editor of the Journal of Computer Graphics Tools, and Editor-in-Chief of ACM Transactions on Graphics. Glassner's many books include the "Graphics Gems" series, the textbook "Principles of Digital Image Synthesis," and the "Andrew Glassner's Notebook" series. His most recent book is "Deep Learning: From Basics to Practice." Glassner has written 3 novels, and directed both film and online entertainment. He holds a PhD from UNC-Chapel Hill. He paints, plays jazz piano, and hikes.

Description: Deep Learning refers to a collection of algorithms that are making significant impacts in computer graphics, just as they have in fields from language translation and medical diagnosis to self-driving cars. The topic is fast becoming an essential part of any technologist's intellectual toolkit. In this course we present a broad overview of the basic concepts behind deep learning for those who want to use these tools for themselves. We share both the core knowledge and the "folk wisdom" that are necessary to design, train, and deploy useful deep learning systems. This course will be accessible to every SIGGRAPH Asia attendee. There's no programming, and the only math is the occasional addition or multiplication. We focus on concepts and principles, not the mechanics of implementation. The course covers a lot of ground, so attendees will learn lots of exciting new ideas. Since many of us are visual thinkers, the course is profusely illustrated. When we're done, you'll understand the basic structure of popular deep learning models, how they work, how they can be efficiently trained, and how to harness these technologies for your own applications.