Watch On:
Summary
Microcontrollers, miniature computers that can run simple commands, are the basis for billions of connected devices, from internet-of-things devices. However, the training process requires so much memory that it is typically done using powerful computers at a data center, before the model is deployed on a device. To address this problem, researchers at MIT and the MIT-IBM Watson AI Lab developed a new technique that enables on-device training using less than a quarter of a megabyte of memory. The first, known as sparse update, uses an algorithm that identifies the most important weights to update at each round of training. Then the algorithm applies a technique called quantization-aware scaling (QAS), which acts like a multiplier to adjust the ratio between weight and gradient, to avoid any drop in accuracy that may come from quantized training. This research from MIT has not only successfully demonstrated the capabilities, but also opened up new possibilities for privacy-preserving device personalization in real-time,” says Nilesh Jain, a principal engineer at Intel who was not involved with this work. “
Show Notes
But cheap, low-power microcontrollers have extremely limited memory and no operating system, making it challenging to train artificial intelligence models on “edge devices” that work independently from central computing resources.
Training a machine-learning model on an intelligent edge device allows it to adapt to new data and make better predictions.
“Our study enables IoT devices to not only perform inference but also continuously update the AI models to newly collected data, paving the way for lifelong on-device learning.
“Innovations in the publication have broader applicability and will ignite new systems-algorithm co-design research.”“On-device learning is the next major advance we are working toward for the connected intelligent edge.
Professor Song Han’s group has shown great progress in demonstrating the effectiveness of edge devices for training,” adds Jilei Hou, vice president and head of AI research at Qualcomm.
Source
https://news.mit.edu/2022/machine-learning-edge-microcontroller-1004
