I can't say I have ever heard of pussy power being used as a driver for advanced chip technology development, but that's precisely what researchers at IBM are claiming. A team of boffins at IBM have been speaking about how they have arrived at something of a milestone breakthrough: a supercomputer that simulates a brain in near real time and has more cerebral cortex capacity than a cat.
The cognitive computing team which is headed up by IBM Research managed to achieve what it says are "significant advances in large-scale cortical simulation" as well as "a new algorithm that synthesizes neurological data" in time for a presentation called 'The cat is out of the bag' at the SC09 supercomputing conference this week.
Together it is being suggested that these advances mean we are getting increasingly close to being able to build not just an advanced computer chip, but a truly cognitive computing chip. That is, in other words, a computer system which can both simulate and emulate the brain’s abilities in terms of sensation, perception, action, interaction and cognition.
The IBM Research scientists, together with colleagues from Lawrence Berkeley National Lab, performed what is said to be the first "real-time cortical simulation of the brain that exceeds the scale of a cat cortex and contains 1 billion spiking neurons and 10 trillion individual learning synapses". Working with researchers from Stanford University, the IBMers also developed a supercomputing algorithm which can "noninvasively measure and map the connections between all cortical and sub-cortical locations within the human brain using magnetic resonance diffusion weighted imaging". This ability to map the internal wiring of the brain is central to the ability to solve the puzzle that is how our brains manage to represent and process so much information.
It doesn't take a genius to realise that the networked world is becoming like a giant brain, massively interconnected and having to process vast amounts of exponentially growing data. "Learning from the brain is an attractive way to overcome power and density challenges faced in computing today" Josephine Cheng, IBM Fellow, says "as the digital and physical worlds continue to merge and computing becomes more embedded in the fabric of our daily lives, it’s imperative that we create a more intelligent computing system that can help us make sense the vast amount of information that's increasingly available to us, much the way our brains can quickly interpret and act on complex tasks".