Deep Learning -An Advance AI To drive House Hold Work
The researchers from Massachusetts Institute of Technology (MIT) have developed a system that could bring deep learning neural networks to new -- and much smaller -- places, like the tiny computer chips in wearable medical devices, household appliances, and the 250 billion other objects that constitute the IoT.
Deep learning — advanced Artificial Intelligence (AI) which is involved with heavy-duty tasks like curating social media and serving Google search — can soon check your vitals or set your thermostat at home and monitor the Internet of Things (IoT).
The researchers from Massachusetts Institute of Technology (MIT) have developed a system that could bring deep learning neural networks to new — and much smaller — places, like the tiny computer chips in wearable medical devices, household appliances, and the 250 billion other objects that constitute the IoT.
The system, called MCUNet, designs compact neural networks that deliver unprecedented speed and accuracy for deep learning on IoT devices, despite limited memory and processing power.
The technology could facilitate the expansion of the IoT universe while saving energy and improving data security.
MCUNet has two components needed for “tiny deep learning” — the operation of neural networks on microcontrollers.
One component is TinyEngine, an inference engine that directs resource management, akin to an operating system.
TinyEngine is optimised to run a particular neural network structure, which is selected by MCUNet’s other component: TinyNAS, a neural architecture search algorithm.
Designing a deep network for microcontrollers isn’t easy.
“It can work pretty well for GPUs or smartphones but it’s been difficult to directly apply these techniques to tiny microcontrollers, because they are too small,” said Ji Lin, a PhD student in Song Han’s lab in MIT’s Department of Electrical Engineering and Computer Science.
Lin developed TinyNAS, a neural architecture search method that creates custom-sized networks.
The customized nature of TinyNAS means it can generate compact neural networks with the best possible performance for a given microcontroller — with no unnecessary parameters.
“Then we deliver the final, efficient model to the microcontroller,” Lin said .
The research will be presented at next month’s Conference on Neural Information Processing Systems.
On a commercial microcontroller they tested, MCUNet successfully classified 70.7 per cent of the novel images — the previous state-of-the-art neural network and inference engine combo was just 54 percent accurate.
“Even a 1 percent improvement is considered significant,” said Lin. “So this is a giant leap for microcontroller settings.”
The promising test results give hope that it will become the new industry standard for microcontrollers. MCUNet could also make IoT devices more secure.
“A key advantage is preserving privacy,” says Han. “You don’t need to transmit the data to the cloud.”