MIT engineers have designed a “brain-on-a-chip,” smaller than a piece of confetti, made from tens of thousands of artificial synapses known as memristors—silicon-based components that can produce and remember signals of varying strength rather than just 1 and 0, thus carrying out a wider range of operations than conventional transistors.
Led by Jeehwan Kim, an associate professor of mechanical engineering, the researchers borrowed from principles of metallurgy to fabricate each memristor from alloys of silver and copper, along with silicon. When tested on several visual tasks, the chip was able to “remember” stored images and reproduce them many times over, in versions that were crisper and cleaner than results achieved by existing memristor designs made with unalloyed elements.
Their results demonstrate promise for neuromorphic devices—electronics based on a new type of circuit that processes information in a way inspired by the human brain. Such circuits could be built into small, portable devices, and would carry out complex computational tasks that today only supercomputers can handle.
“So far, artificial synapse networks exist as software. We’re trying to build real neural-network hardware for portable artificial-intelligence systems,” says Kim. “Imagine connecting a neuromorphic device to a camera on your car, and having it recognize lights and objects and make a decision immediately.” He adds, “Someday you might be able to carry around artificial brains to do these kinds of tasks, without connecting to supercomputers, the internet, or the cloud.”