'Human brain' circuit board works 9,000 times faster than a PC

Scientists at Stanford University hope the Neurogrid could be used to develop prosthetic limbs

Antonia Molloy
Saturday 03 May 2014 17:10 BST
Comments

The human brain remains largely an enigma; full of unharnessed potential and capable of outsmarting even the most high-tech modern computers.

But a new circuit board developed by scientists at Stanford University in California could help people to understand the true power of their own minds.

The Neurogrid, which is modelled on the human brain, can simulate one million neurons and billions of synapses, or brain connections – far more than other “brain-mimicking” devices.

It is about the size of an iPad and consists of 16 custom-designed “Neurocore” chips, which are 9,000 times faster, and more energy-efficient, than a typical computer, Live Science reported.

Kwabena Boahen, associate professor of bioengineering at Stanford, said: “From a pure energy perspective, the brain is hard to match.”

But Boahen and his fellow bioengineers hope the project could pave the way for advances in robotics and computing, and lead to new ways of understanding how the brain works.

Researchers are now working with other Stanford scientists to develop prosthetic limbs that would be controlled by a Neurocore-like chip. The chip would decode brain signals into movements without overheating the brain.

Currently, only individuals with an understanding of the human brain can programme the Neurogrid – but Boahen plans to create a “neurocompiler” that would allow scientists and engineers without neuroscience knowledge to use the device.

The Neurogrid is just the latest cog in the wheel of an international effort to understand the human brain, including the European Union's Human Brain Project, which aims to simulate a human brain on a supercomputer.

The Stanford researchers are working under the US BRAIN (Brain Research through Advancing Innovative Neurotechnologies) Project, which challenges scientists to develop new tools for measuring brain activity.

Boahen said Neurogrid is the most cost-effective effort developed so far, but each circuit board still costs about $40,00 so the researchers are now working to reduce the cost 100-fold.

However, there’s still a long way to go in terms of matching the power of the human brain.

Boahen said: “The human brain, with 80,000 times more neurons than Neurogrid, consumes only three times as much power. Achieving this level of energy efficiency while offering greater configurability and scale is the ultimate challenge."

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Comments

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in