After 20 years in conception, 12 years in construction, and £15 million in funding, the world’s largest neuromorphic supercomputer designed to function like the human brain was switched on for the very first time Friday, November 2. Developed by University of Manchester researchers, the Spiking Neural Network Architecture (SpiNNaker) machine is armed with a processor core that’s 1 million strong, with each chip having 100 million transistors.
Basic brain cells within the nervous system are known as biological neurons. They communicate by emitting “spikes” of electro-chemical energy. Transitioning this occurrence into technology, neuromorphic computing utilizes large-scale computer systems with electronic circuits to mirror these spikes through man-made means.
The supercomputer can model more biological neurons in real time than any other machine on Earth, according to the University of Manchester. It’s also unique in its design, since it mimics the brain’s parallel communication architecture by “sending billions of small amounts of information simultaneously to thousands of different destinations.”
“SpiNNaker completely re-thinks the way conventional computers work,” says Steve Furber, Professor of Computer Engineering, who first conceived the idea of such a project. “We’ve essentially created a machine that works more like a brain than a traditional computer, which is extremely exciting. The ultimate objective for the project has always been a million cores in a single computer for real-time brain modelling applications, and we have now achieved it, which is fantastic.”
Researchers hope to use SpiNNaker to up our knowledge of the brain’s inner workings. The team has already been able to simulate certain brain segments, running an 80,000 neuron model of a portion of the cortex. It has also simulated the Basal Ganglia region of the brain, which is an area affected by Parkinson’s disease.
Furthermore, SpiNNaker has been able to control the SpOmnibot, a robotic platform developed by Technische Universität München. SpiNNaker allows the robot to use real-time interpretation of visual data, as well as navigation benefits.
“Neuroscientists can now use SpiNNaker to help unlock some of the secrets of how the human brain works by running unprecedentedly large scale simulations. It also works as real-time neural simulator that allows roboticists to design large-scale neural networks into mobile robots so they can walk, talk, and move with flexibility and low power,” says Professor Furber.
The researchers hope to ramp up the supercomputer to handle more than 1 billion biological neuron in real time. According to the University of Manchester, that figure is 1 percent the scale of the human brain’s 100 billion brain cell (neuron) network. To increase the complexity, 1 quadrillion synapses interconnect the entire system.