Mosaic ML
Mosaic ML
The goal of Mosaic ML is making ML training efficient, and to improve efficiency of neural network training with algorithmic methods that deliver speed, boost quality and reduce cost.
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.