A SMART ROBOT ARM might be something from the fevered mind of sci-fi fans, but they could be closer to reality then one might imagine, thanks to Intel's Pohoiki Beach.
That's the name given to the company's new 64-chip 'neuromorphic' system, which can chew through deep learning tasks with more aplomb than your garden variety processor.
That first bit sounds like gobbledygook, but it's actually the name given to deep learning chips that learn like human brains do, with artificial neurons connected by pseudo synapses.
Intel's work on such stuff resulted in the Loihi chip, which the chipmaker said can process information 1,000 times faster and 10,000 more efficiently than"CPUs for specialised applications like sparse coding, graph search and constraint-satisfaction problems".
And Pohoiki Beach has 64 of them, meaning it has some eight million neurons to bring to bear on deep learning workloads.
This is not a system you're going to find in your local computer shop, rather it's a system designed for AI researchers and developers.
"We are impressed with the early results demonstrated as we scale Loihi to create more powerful neuromorphic systems. Pohoiki Beach will now be available to more than 60 ecosystem partners, who will use this specialized system to solve complex, compute-intensive problems," said Rich Uhlig, managing director at Intel Labs.
But what's particularly interesting about the system is that it could be used to power autonomous systems like self-driving cars with greater speed and efficiency than current systems used to crunch smart algorithms.
Pohoiki Beach could even pave the way for smart prosthetic limbs. Intel touted an example in the form of the AMPRO robotic prosthetic leg, which could be given more adaptive capabilities. It also noted that the tech could deliver improved object tracking through event-based cameras - cameras the react to specific movements or changes in a scene - and even giving a robot skin that can detect tactile input, potentially making robot that could feel.
Much a (dil)do about nothing
Neither the time nor the face
The tiny tweaks are coming thick and fast now
Gitting more secure