Skip to main content
MIT Corporate Relations
MIT Corporate Relations
Search
×
Read
Watch
Attend
About
Connect
MIT Startup Exchange
Search
Sign-In
Register
Search
×
MIT ILP Home
Read
Faculty Features
Research
News
Watch
Attend
Conferences
Webinars
Learning Opportunities
About
Membership
Staff
For Faculty
Connect
Faculty/Researchers
Program Directors
MIT Startup Exchange
User Menu and Search
Search
Sign-In
Register
MIT ILP Home
Toggle menu
Search
Sign-in
Register
Read
Faculty Features
Research
News
Watch
Attend
Conferences
Webinars
Learning Opportunities
About
Membership
Staff
For Faculty
Connect
Faculty/Researchers
Program Directors
MIT Startup Exchange
5.5.22-Efficient-AI-Song-Han
Conference Video
|
Duration: 26:40
May 5, 2022
View this past event
Preview
5.5.22-Efficient-AI-Song-Han
Please
login
to view this video.
Video details
Modern deep learning requires a massive amount of computational resources, carbon footprint, and engineering efforts. On mobile devices, the hardware resource and power budget are very limited, and on-device machine learning is challenging; retraining the model on-device is even more difficult. We make machine learning efficient and fit tiny devices (TinyML). Our research is highlighted by full-stack optimizations, including the neural network topology, inference library, and the hardware architecture, which allows a larger design space to unearth the underlying principles.
Locked Interactive transcript
Please
login
to view this video.
Video details
Modern deep learning requires a massive amount of computational resources, carbon footprint, and engineering efforts. On mobile devices, the hardware resource and power budget are very limited, and on-device machine learning is challenging; retraining the model on-device is even more difficult. We make machine learning efficient and fit tiny devices (TinyML). Our research is highlighted by full-stack optimizations, including the neural network topology, inference library, and the hardware architecture, which allows a larger design space to unearth the underlying principles.
Locked Interactive transcript
More Videos From This Event
See all videos
May 2022
|
Conference Video
5.5.22-Efficient-AI-Julie-Shah
The Ethical Computing Platform
May 2022
|
Conference Video
5.5.22-Efficient-AI-Daniel-Huttenlocher
Building the Schwarzman College of Computing at MIT
May 2022
|
Conference Video
5.5.22-Efficient-AI-Michael-Carbin
Efficient ML by Approximation
May 2022
|
Conference Video
5.5.22-Efficient-AI-Jesús-delAlamo
AI Hardware: What’s Next?
May 2022
|
Conference Video
5.5.22-Efficient-AI-Panel
MIT-Industry Panel Discussion: AI Hardware at the Edge - the Internet of Intelligent Things
May 2022
|
Conference Video
5.5.22-Efficient-AI-Wojciech-Matusik
High-resolution Tactile Sensors to Give AI a Human-Touch
May 2022
|
Conference Video
5.5.22-Efficient-AI-Dina-Katabi
Ambient Intelligence: Seeing the World Through the Eyes of Radio Signals
May 2022
|
Conference Video
5.5.22-Efficient-AI-Tomás-Palacios
AI Talent Recruiting: MIT EECS Alliance
May 2022
|
Conference Video
5.5.22-Efficient-AI-Sync-Computing
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-Covariance
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-Interpretable-AI
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-Themis-AI
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-UbiCept
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-Prescient
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-MosaicML
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-OmniML
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-Arundo
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-Pison
MIT Startup Lightning Talk
May 2022
|
Conference Video
5.5.22-Efficient-AI-Antonio-Torralba
Learning to See by Looking at Noise
May 2022
|
Conference Video
5.5.22-Efficient-AI-Sertac-Karaman
Chips for Robotics: The Co-design of Computing Hardware and Algorithms for Low-energy Autonomous Vehicles