Bharat SainiLast Updated on December 28, 2018 by Bharat Saini
SpiNNaker, world’s fastest brain-mimicking machine, a novel computer architecture inspired by the working of the human brain, a supercomputer with a million processing cores and 1200 interconnected circuit boards that together operate like a human brain, was switched on for first time by the Researchers in the UK on 2 November 2018. A special computer chip that consists of 18 tightly-packed processor cores is at the heart of the machine. Over 55000 of these chips were linked together to endow the supercomputer with a million processor cores altogether that are coordinated using a new type of computer design known as the SpiNNaker.
SpiNNaker or the Spiking Neural Network Architecture is a many-core computer architecture designed by the Advanced Processor Technologies Research Group at the School of Computer Science, University of Manchester in the UK, led by Steve Furber, to simulate the human brain. It has been under construction since 2006 with over £15 million in funding. This landmark neuromorphic computer is capable of modelling more biological neurons in real-time than any other machine currently in existence. It uses 1 million ARM processors in a massive parallel computing platform based on Spiking Neutral Networks.
SpiNNaker is being used as one component of the neuromorphic computing platform for the Human Brain Project. Steve Furber said, it “rethinks the way conventional computers work.” But SpiNNaker doesn’t just “think” like a brain. It creates models of the neurons in human brains, and it simulates more neurons in real time than any other computer on Earth.
Steve Furber explained: “Its primary task is to support partial brain models: for example, models of cortex, of basal ganglia, or multiple regions expressed typically as networks of spiking [or firing] neurons.”
- “We’ve essentially created a machine that works more like a brain than a traditional computer, which is extremely exciting.”
- In the human brain, 100 billion neurons simultaneously fire and transmit signals to thousands of destinations.
- SpiNNaker’s architecture supports an exceptional level of communication among its processors, behaving much like a brain’s neutral network does.
- SpiNNaker now it has the capacity to perform 200 quadrillion actions simultaneously.
- SpiNNaker can also control a mobile robot called SpOmnibot, which uses the computer to interpret data from the robot’s vision sensors and make navigation choices in real time.
- SpiNNaker, with all its computing power and brain-like capabilities, can still manage only a fraction of the communication performed by a human brain, and supercomputers have a long way to go before they can think for themselves.
- “Even with a million processors, we can only approach 1 percent of the scale of the human brain, and that’s with a lot of simplifying assumptions.”
- However, SpiNNaker could mimic the function of a mouse brain, which is 1000 times smaller than a human brain..
- “If a mouse thinks mouse-sized thoughts and all that is required is enough neurons wired together in the right structure (which is itself a debatable point), then maybe we can now reach that level of thinking in a model running on SpiNNaker.”
Neuromorphic computing, using computers to mimic the brain, is a rapidly growing area of computer science research that focuses on developing system architectures and specialized computer chips that replicate the way the human brain processes information. This will allow neuroscientists to create unprecedented models of the brain and allow roboticists to create robots that can navigate complex environments using computer vision.
