Neural chip performs AI tasks
Researchers from Massachusetts Institute of Technology (MIT), USA, have developed a new energy-efficient neural chip that can run powerful artificial intelligence (AI) algorithms locally, without depending on the Internet for heavy data processing. The chip is called Eyeriss and is ten times as efficient as a mobile GPU, and can possibly increase the task-handling capability of mobile devices.
A neural network is a vast virtual network of information processors, modelled to emulate the processing technique of the human brain. It is used to execute powerful computational processes and to run algorithms that are too heavy for a single low-power device to handle.
Eyeriss has 168 cores, and each of these has its own memory unlike a single, shared memory bank found in other GPUs. Hence, the cores would not have to transmit data back and forth the memory bank, thus saving time and energy. This also facilitates communication between individual cores without the need for it to be routed through the main memory.