female hand using smartphone with icon technology artificial intelligence (AI) and internet of things (IOT)

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.