TinyML: Enable Efficient Deep Learning on Mobile Devices
Song Han
This project pursues efficient machine learning for mobile devices where hardware resources and energy budgets are very limited.
A Foolproof Way to Shrink Deep Learning Models
Kim Martineau | MIT Quest for Intelligence
MIT researchers have proposed a technique for shrinking deep learning models that they say is simpler and produces more accurate results than state-of-the-art methods.
Faster Video Recognition for the Smartphone Era
Kim Martineau | MIT Quest for Intelligence
A new technique for training video recognition models is up to three times faster than current state-of-the-art methods while improving runtime performance on mobile devices.