IBM Creates Software Environment for Brain-like Chips
Researchers making chips and software to think like you do.
Despite how weak we may be with precise calculations, the human brain is still remarkably complex and unmatched when processing qualitative data. In 2011, IBM developed computing chips, dubbed SyNAPSE, that simulates some of the brain's functions. Now the next step is to create a software ecosystem for the hardware, which is radically different than the programming environments available for today's common chips.
"Architectures and programs are closely intertwined and a new architecture necessitates a new programming paradigm," said Dr. Dharmendra S. Modha, Principal Investigator and Senior Manager, IBM Research. "We are working to create a FORTRAN for synaptic computing chips. While complementing today's computers, this will bring forth a fundamentally new technological capability in terms of programming and applying emerging learning systems."
IBM's developed a simulator, neuron model, programming model, library, laboratory to help support the programming cycle from design through development, debugging, and deployment.
Through the new software environment, IBM hopes to further the development of smarter sensors. Human eyes with the visual cortex interpret over a terabyte of data daily. If replicable, eyeglasses with SyNAPSE could help the visually impaired.
Another example given by IBM research is for standalone applications, such using SyNAPSE in a search-and-rescue robot that's able to capture and process information in areas that would be unsafe for humans.
IBM states that its long-term goal is "to build a chip system with ten billion neurons and hundred trillion synapses, while consuming merely one kilowatt of power and occupying less than two liters of volume."
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
-
JPNpower The day may come when you will upload your brain to a machine on your deathbed. Then all that philosophy stuff begins, whether you still live on or not.Reply -
memadmax I dunno why you would want to model a computing system after the human brain... Yea, sure, the brain is powerful, but it is much too flawed for computing environments, we can't precisely do anything more than once, for example. The only other reason why you would want to build one of these things is for social type crap, such as a robotic woman that doesn't scream at you for leaving the toilet seat up... for example >_>Reply -
gm0n3y Getting the hardware built is just a matter of time, figuring out how to best write software for it will be the real difficulty. Similar to programming using DNA (which is horrendously complex/difficult on all but the simplest strands), nature has had billions of years of trial and error to come out with complex organisms that function reasonably well (the human brain is amazing but certainly not infallible). We can try to modify existing life, but coming up with our own from scratch is far beyond current capabilities.Reply -
Achoo22 If the tech were really like a human brain, wouldn't it be more efficient to teach it than program it?Reply