October 5, 2015

Rack your brains over brains running on racks

This month's issue of Nature delivers a special on the brain that really gets you thinking. They take a detailed look at how Europe's Human Brain Project and the US BRAIN initiative are taking shape but the real prize is this interesting write-up on some of the most promising currently existing neuromorphic hardware. Check out Neurogrid, SpiNNaker, BrainScaleS, SyNAPSE and the neural net simulation called Spaun.

Here's a collection of interesting bits from the article that will make you click onwards to read the thing in full.

Just a few years ago, Kwabena Boahen completed a device called Neurogrid that emulates a million neurons, about as many as there are in a honeybee's brain. Now applications for 'neuromorphic technology' are finally in sight.

In 2012 Boahen contacted Chris Eliasmith, who is responsible for Spaun: a design for a computer model of the brain that includes the parts responsible for vision, movement and decision-making. Previously, a simulation of Spaun on a conventional computer had shown that, with 2.5 million simulated neurons plus a simulated retina and hand, it could copy handwritten digits, recall the items in a list, work out the next number in a given sequence and carry out several other cognitive tasks. But the Spaun simulation ran about 9,000 times slower than real time, taking 2.5 hours to simulate 1 second of behaviour.

Boahen contacted Eliasmith with the obvious proposition: build a physical version of Spaun using real-time neuromorphic hardware. “I got very excited,” says Eliasmith, for whom the match seemed perfect. “You've got the peanut butter, we've got the chocolate!”

With funding from the US Office of Naval Research, Boahen and Eliasmith have put together a team that plans to build a small-scale prototype in three years and a full-scale system in five. For sensory input they will use neuromorphic retinas and cochleas developed at the INI, says Boahen. For output, they have a robotic arm. But the cognitive hardware will be built from scratch.

The system is explicitly designed for real-world applications. On a five-year timescale, says Boahen, “we envision building fully autonomous robots that interact with their environments in a meaningful way, and operate in real-time while [their brains] consume as much electricity as a cell phone”. Such devices would be much more flexible and adaptive than today's autonomous robots, and would consume considerably less power.

In the longer term, Boahen adds, the project could pave the way for compact, low-power processors in any computer system, not just robotics. If researchers really have managed to capture the essential ingredients that make the brain so efficient, compact and robust, then it could be the salvation of an industry about to run into a wall as chips get ever smaller.

“But we won't know for sure,” Boahen says, “until we try.”

> http://www.nature.com/news/neuroelectronics-smart-connections-1.14089
> Neurogrid; http://www.stanford.edu/group/brainsinsilicon/neurogrid.html
> SpiNNaker; http://apt.cs.man.ac.uk/projects/SpiNNaker/
> BrainScaleS - http://brainscales.kip.uni-heidelberg.de/
> SyNAPSE - http://www.research.ibm.com/cognitive-computing/neurosynaptic-chips.shtml
> Spaun; http://nengo.ca/build-a-brain/spaunvideos

No comments:

Post a Comment