Designing Efficient
Deep Learning Systems

Brain Icon

From Smart to Deep: Unraveling the Complex Sub-World of AI

Deep learning is undeniably impressive. Computers can now recognize objects in images and transcribe speech to text better than humans can.

But deep learning uses highly complex neural networks that require a significant amount of computation to operate. This can make it difficult to use in many real-world scenarios where resources are limited or real-time operation is critical. MIT’s new course, Designing Efficient Deep Learning Systems, provides a clear look at the key building blocks of deep learning and how organizations can build hardware systems that enable wide deployment of deep learning solutions.

MIT’s new course, Designing Efficient Deep Learning Systems, provides a clear look at what deep learning is and how organizations can take advantage of it when implementing their hardware systems. Course participants will learn:

Accelerating the Silicon Valley Surge

For over 65 years, MIT Professional Education Short Programs courses have been held on-campus in Cambridge, MA. But this upcoming spring, MIT Professional Education is also heading West to California. The debut session of Designing Efficient Deep Learning Systems will take place March 26-27, 2018 in the Intelligence Innovation Lab at Samsung Research America (SRA) Headquarters in Mountain View - the heart of Silicon Valley and home to some of the world's top AI start-ups.

Interested?

Sign up to receive updates when Designing Efficient Deep Learning Systems opens for registration.

For special bulking pricing, please contact shortprograms@mit.edu

Sign Up

Our First Course on the West Coast

Designing Efficient Deep Learning Systems will first be offered at Samsung Research America's (SRA) innovative campus in Mountain View, CA. SRA is at the forefront of computer science research. The Intelligence Lab does research into future generations of AI and their applications. Join us for our inaugural West Coast course!


Samsung Research America
665 Clyde Avenue
Mountain View, CA 94043

Network Icon

About the Faculty

Vivian Sze

The Designing Efficient Deep Learning Systems course is led by Vivienne Sze, an Associate Professor of Electrical Engineering and Computer Science at MIT. Sze is part of a team at researchers at MIT working to bring neural networks to handheld devices. The team recently developed an energy-efficient chip named Eyeriss that could allow neural networks to run on smartphones. Prof. Sze and her collaborators (Joel Emer and Yu-Hsin Chen) have given tutorials on deep learning hardware at numerous top-tier hardware conferences as well as developed an undergraduate/graduate course on this topic at MIT. Now, she is looking to share her knowledge of current tools, algorithms, and strategies for neural network design with other professionals in the industry.

Sze is a recipient of the 2017 Qualcomm Faculty Award, 2016 Google Faculty Research Award, the 2016 MICRO Top Picks Award, the 2016 AFOSR Young Investigator Research Program Award, the 2016 3M Non-Tenured Faculty Award, the 2014 DARPA Young Faculty Award, the 2007 DAC/ISSCC Student Design Contest Award and a co-recipient of the 2008 A-SSCC Outstanding Design Award.

Current research topics include:

Learn more about Prof. Sze's research.

Door Icon

Why MIT Professional Education?

MIT Professional Education delivers timely programs on new technology to a global audience of working professionals in industry, government and academia. MIT Professional Education’s mission is to provide a gateway to renowned MIT research, knowledge and expertise for those engaged in science and technology worldwide, through advanced, practitioner-oriented education programs designed for them. All programs are delivered by MIT faculty who promote technical excellence and advancement through ongoing educational engagement with communities of practice. Under the umbrella of the School of Engineering, MIT Professional Education supports the development of innovative leaders equipped to address world’s most complex challenges.

For more information visit http://professional.mit.edu