LIVING ROBOT with 'HUMAN BRAIN' close to creation as super AI computer around the corner
Engineers at the University of Massachusetts are developing microprocessors which mimic biological synapses - the nerve cells which pass messages across the human body.
The science fiction-style project is being undertaken by Joshua Yang and Qiangfei Xia, professors of electrical and computer engineering at the US college.
Their work focuses heavily on memristors - a computer component which could change science forever, switching the focus from electronics to ionics.
Ionics, unlike electronics, is not dependent on a power source. It essentially has a memory, so even if it loses power it can remember what it was doing before and continue the action.
This means computers of the near-future will be able to shut on and off like a lightbulb, not losing any data or files in the process.
Different researchers and developers, including Mr Yang and Mr Xia, are now racing to be the first to harness this technology and use it to create a new generation of computers.
Professor Jennifer Rupp said: “I think there is a race going on. There is a strong driving force, but at the same time it's very important that there are players like HP, because they want to get to the market, show everyone that this is real.”
Mr Yang and Mr Xia explained the process in more detail in their report, explaining the process behind neuromorphic computing - computers which mimic humans.
They said: “Memristors have become a leading candidate to enable neuromorphic computing by reproducing the functions in biological synapses and neurons in a neural network system, while providing advantages in energy and size.
“This work opens a new avenue of neuromorphic computing hardware based on memristors.
“Specifically, we developed a diffusive-type memristor where diffusion of atoms offers a similar dynamics and the needed time-scales as its bio-counterpart, leading to a more faithful emulation of actual synapses, i.e. a true synaptic emulator.
“The results here provide an encouraging pathway toward synaptic emulation using diffusive memristors for neuromorphic computing."
( Source )