An introductory course on deep learning methods with applications to machine translation, image recognition, game playing, image generation and more. A collaborative course incorporating labs in TensorFlow and peer brainstorming along with lectures. Course concludes with project proposals with feedback from staff and panel of industry sponsors.
This version of the course is outdated, please refer to our homepage for an updated version.
Jan 29 - Feb 2
10:30am-1:30pm, MIT Room 32-123
10:30am-11:15pm: Lecture Part 1
11:15am-12:00pm: Lecture Part 2
12:00pm-12:30pm: Snack Break
12:30pm-1:30pm: Lab (Hands-On TensorFlow Labs)
Project proposals will be 1-minute pitches of a novel deep learning algorithm, application, open-source contribution, plan to create an interesting dataset, or other contributions. Sponsors will judge and select top projects as award winners. Alternative to project proposal is to submit a 1-page review of an interesting deep learning paper.
If you are an MIT student (undergraduate or graduate) please register by submitting an add-drop form here. You can do this by clicking "create new form" and selecting "Add Drop". Enter the subject information (6.S191) and 3 units when prompted. You can also specify if you want to be registered as a listener or regular student there. If you would like to receive course related updates and lecture materials please sign up for our mailing list.
3 units P/D/F based on completion of project proposal assignment
Reach out to [email protected].
| Session | Part 1 | Part 2 | Lab |
| 1 |
Introduction to Deep Learning
[Slides] [Video]
|
Deep Sequence Modeling
[Slides] [Video]
|
Intro to TensorFlow, Music Generation with RNNs
[Code]
|
| 2 |
Deep Computer Vision
[Slides] [Video]
|
Deep Generative Models
[Slides] [Video]
|
Disease Detection from Human X-Ray Scans
[Code]
|
| 3 |
Deep Reinforcement Learning
[Slides] [Video]
|
Limitations and New Frontiers
[Slides] [Video]
|
Work time for paper reviews/project proposals
|
| 4 |
Guest Lecture: Google
[Info] [Video1] [Slides2] [Video2]
|
Guest Lecture: NVIDIA
[Info] [Slides] [Video]
|
Sponsor Booths + Work time for paper reviews/project proposals
|
| 5 |
Guest Lecture: IBM
[Info] [Slides] [Video]
|
Guest Lecture: Tencent
[Info] [Video]
|
Project Proposal Presentations, Judging and Awards
|
Lead Organizer
Lead Organizer
Co-Chair
Co-Chair
Aaron Courville is an Assistant Professor in the Department of Computer Science and Operations Research (DIRO) at the University of Montreal, and member of MILA (Montreal Institute for Learning Algorithms). Courville is a co-author of the textbook, Deep Learning, along with Ian Goodfellow and Yoshua Bengio.
Urs Muller joined NVIDIA in early 2015 to build and lead an autonomous driving team that creates novel deep-learning solutions for self-driving cars on NVIDIA's high-performance DRIVE PX platform. Previously, Muller worked at Bell Labs and later founded Net-Scale Technologies, Inc., a prime contractor on several robotics and machine learning DARPA programs.
D. Sculley leads teams in Google Brain focused on TensorFlow Usability, ML Fairness, Bayesian Optimization, and general deep learning research. He is located in Google's Cambridge, MA office, which has a wide array of ML opportunities and projects.
Shanqing Cai has been working for the past two years to help make model development in TensorFlow as easy and transparent as possible. He has led the development of the TensorFlow Debugger, among many contributions in this space.
Dr. Lisa Amini is the Director of IBM Research Cambridge, and Acting IBM Director of the newly announced MIT-IBM Watson AI Lab. The MIT-IBM Watson AI Lab is dedicated to fundamental artificial intelligence (AI) research with the goal of propelling scientific breakthroughs in four research pillars: AI Algorithms, the Physics of AI, the Application of AI to industries, and Advancing shared prosperity through AI; all of which leverage and pioneer machine learning, deep learning, and machine reasoning algorithms.
Lin Ma is a Principal Researcher at Tencent AI Lab based in Shenzhen, China. His current research interests lie in the areas of computer vision and deep learning, such as image/video processing, analysis, and understanding. Previously, he was a Researcher with Huawei Noah's Ark Lab, Hong Kong. Lin Ma received his Ph.D. degree in Department of Electronic Engineering at the Chinese University of Hong Kong (CUHK) in 2013. He received the B. E., and M. E. degrees from Harbin Institute of Technology, Harbin, China, in 2006 and 2008, respectively, both in computer science. He was a finalist to HKIS young scientist award in engineering science in 2012. He was awarded the Microsoft Research Asia fellowship in 2011.
