The future of computing is anything but conventional, says J. Joshua Yang, UMass Amherst professor of electrical and computer engineering. He believes that processes in the human brain called neuromorphic computing hold promise for taking computing far beyond its current energy efficiency and processing limitations. “In this era of big data and the internet of things, we are faced with tons of data,” says Yang. “Our devices must be able to process things faster while using less energy.”
Yang and his colleagues have developed a diffusive memristor, a tiny electrical resistance switch that can faithfully emulate the synapses where signals pass from one nerve cell to another in the human brain. These devices can store and process information while offering several key performance characteristics that exceed conventional integrated circuitry. Their manufacture doesn’t require exotic materials or high temperatures and they can be used for different purposes such as memory storage, information processing, security, and as a sensor.
J. Joshua Yang, Electrical and
“We’re looking at how human brains process and store information,” says Yang. “We wanted to build something with real intelligence—computers that can really think and learn, not just use software and human-programmed algorithms.”
Universal memory is one application Yang sees for memristive technology. “Right now,” he says, “we have memory hierarchies, different types of memory with different attributes and performance. We need a universal memory designed to be good at everything—to be fast, dense, and nonvolatile and have low energy requirements. Universal memory means a much simpler computer in terms of components, one that will use less energy, store more information, and be faster. We’ll be able to process the same information with orders of magnitude less energy and faster speed.”
Yang’s diffused memristor is just one building block in neuromorphic computing. “We now want to emulate a neuron” he says, “then integrate synapses and neurons together to build a neural network; that’s what’s next. We will pick the neuroscientists’ brains to get their latest knowledge to implement in our electronic platform. This will help the neuroscientists, too. We may have a better platform to verify their theories of the brain than animal tissues, which is still pretty much a black box. Our electronic system is well defined and can be checked. It can help us get answers. It’s also a great natural platform for novel computing paradigms.” Visit the Yang lab to learn more.