A team of US researchers has built an energy-friendly chip that can
perform powerful artificial intelligence (AI) tasks, enabling future
mobile devices to implement "neural networks" modelled on the human
The team from Massachusetts Institute of Technology (MIT)
developed a new chip designed specifically to implement neural networks.
It is 10 times as efficient as a mobile GPU (Graphics Processing
Unit) so it could enable mobile devices to run powerful AI algorithms
locally rather than uploading data to the Internet for processing.
The GPU is a specialised circuit designed to accelerate the image output in a frame buffer intended for output to a display.
smartphones are equipped with advanced embedded chipsets that can do
many different tasks depending on their programming.
GPUs are an
essential part of those chipsets and as mobile games are pushing the
boundaries of their capabilities, the GPU performance is becoming
Neural nets were widely studied in the
early days of artificial intelligence research, but by the 1970s, they
had fallen out of favour. In the past decade, however, they have come
back under the name "deep learning."
"Deep learning is useful for
many applications such as object recognition, speech and face
detection," said Vivienne Sze, assistant professor in MIT's department
of electrical engineering and computer science, in a MIT statement.
new chip, which the researchers dubbed "Eyeriss," can also help usher
in the "Internet of things" - the idea that vehicles, appliances,
civil-engineering structures, manufacturing equipment, and even
livestock would have sensors that report information directly to
networked servers, aiding with maintenance and task coordination.
powerful AI algorithms on board, networked devices could make important
decisions locally, entrusting only their conclusions, rather than raw
personal data, to the Internet.
The team presented their findings at the "International Solid State Circuits Conference" in San Francisco recently.
the conference, the MIT researchers used "Eyeriss" to implement a
neural network that performs an image-recognition task. It was for the
first time that a state-of-the-art neural network has been demonstrated
on a custom chip.
"This work is very important, showing how
embedded processors for deep learning can provide power and performance
optimizations that will bring these complex computations from the cloud
to mobile devices," explained Mike Polley, senior vice president at
Samsung's mobile processor innovations lab.