"Technique Enables AI on Edge Devices to Keep Learning over Time"

A team of researchers from MIT, the MIT-IBM Watson AI Lab, and other organizations developed a method for deep learning models to efficiently adapt to new sensor data directly on an edge device, thus increasing security and more. Personalized deep learning models can power Artificial Intelligence (AI) chatbots that adapt to understand a user's accent, as well as smart keyboards that regularly update to better predict the next word based on a user's typing history. This customization requires constant Machine Learning (ML) model fine-tuning with new data. Since smartphones and other edge devices lack the memory and computational power required for fine-tuning, user data is typically uploaded to cloud servers, where the model is updated. However, data transmission consumes a lot of energy, and sending sensitive user data to a cloud server is a security risk. This article continues to disucss the ML technique developed by the team.

MIT News reports "Technique Enables AI on Edge Devices to Keep Learning over Time"

Submitted by grigby1