IBM creates cognitive semiconductors: A step toward right brain computers

IBM creates cognitive semiconductors: A step toward right brain computers

Summary: Cognitive computing systems are designed to emulate the brain's ability to absorb information and adapt to an environment. In the future, your data center may come complete with left brain and right brain racks.

SHARE:

IBM on Thursday will unveil experimental semiconductors that aim to match the human brain and its ability to interpret its surroundings and learn. The development could lead to a series of "right brain" computers.

Simulation of IBM's chip. Source: IBM

These so-called cognitive chips have two prototypes that are currently being tested. The semiconductors were created out of standard technology in IBM's fabrication plant. Both cores were fabricated in a 45 nanometer process and feature 256 neurons. One core contains 262,144 programmable synapses---basically the social network in the chip---and 65,536 learning synapses. IBM has demonstrated navigation, machine vision, pattern recognition, associative memory and classification with these chips.

What do these cognitive chips add up to? Dharmendra Modha, a project leader for IBM Research, said these new prototype chips can lead to systems that complement today's computers. Computers today revolve around structured data and various calculations, said Modha. Cognitive computers would be more about processing unstructured data and various inputs.

Map of the brain's network connections. Source: IBM

"These cognitive chips can create a new generation of computers to complement today's. Today's computer would be left brain---fast, analytical, rational and structured---the cognitive side would be the other side, which is slow, low power and unstructured. It's right brain to left brain," explained Modha. "Bringing this technology forward completes the computing tool chest."

In many respects, the brain---which packs a lot of low power computational heft in a tight space---is the Holy Grail of computing. Big Blue is looking to put these chips together to recreate the neurons and synapses in biological systems (right).

Add it up and computing today is basically operating with half a brain---the left side.

The upshot is that these chips could be cobbled together to correlate data, create hypotheses and remember things. The product of these chips would be a cognitive computer, according to IBM.

IBM said the research effort behind the project combines disciplines such as neuroscience, nanotechnology and supercomputing. Defense Advanced Research Projects Agency (DARPA) has awarded IBM and a team of university researchers $21 million to carry out the second phase of a project dubbed the Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) project.

Columbia University; Cornell University; University of California, Merced; and University of Wisconsin, Madison worked with IBM on the project. Modha said IBM had been working on cognitive computing for about six years. DARPA started investigating the topic three years ago. When the timing---and funding---lined up the effort to create cognitive systems picked up steam. "DARPA demands dream on a deadline," said Modha. "That's how fast paced (development) is."

IBM sees multiple applications for these cognitive computing systems, which would fit in the size of a shoebox. Among potential uses:

  • Computers that could take in inputs such as texture, smell and feel to gauge whether food was outdated.
  • Financial applications to monitor trading and recognize patterns in a way today's algorithms can't.
  • Traffic monitoring.
  • And system monitoring for waterways and other natural resources.

These cognitive systems could have multiple uses. In the future, your data center may come complete with left brain and right brain racks.

Topics: Networking, CXO, Hardware, IBM, Processors

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.

Talkback

9 comments
Log in or register to join the discussion
  • RE: IBM creates cognitive semiconductors: A step toward right brain computers

    "basically the social network in the chip"

    Did you mean neural network?

    "Financial applications to monitor trading and recognize patterns in a way today?s algorithms can?t."

    That won't happen, since this chip should be using... well, today's algorithms to train their hardware neural networks. If IBM is suggesting that the systems will be able to function much faster in hardware than in software and thus tackle learning problems that would require supercomputers to do with software, that might be the case.
    jgm@...
    • RE: IBM creates cognitive semiconductors: A step toward right brain computers

      @jgm@... very good response. well put.
      Peter.Perhac
    • RE: IBM creates cognitive semiconductors: A step toward right brain computers

      @jgm@...
      Read the book "On Intelligence" by Jeff Hawkins who describes his vision/design for machine intelligence employing the functions/architecture of the neo-cortex using a unifying algorithm. These chips are modeled after Hawkins vision.

      The author of this article does not mean neural networks when talking about a social network. I believe, that the term social network, as the article?s author employs, refers to the ability of the 262,144 synapses to interrelate as they follow the 4 rules of cortical memory - (1) they store patterns, (2) they are generally self-aware & auto-associate or talk to others with similar patterns, (3) invariant forms are stored (read Hawkin?s book), and finally (4) a hierarchy is formed from the stored patterns. From Hawkins perspective neural networks and AI are dead ends in modeling brain-like behavior since at most they can do is mimic a desired behavior and form artificial decisions.

      The goal of this chip is not to ?function much faster in hardware than in software and thus tackle learning problems.? Related to computational tasks, our brains cannot function nearly as fast as our computers. However, in making decisions we win hands down. I believe that?s what this chip is designed for ? using (stored-patterned) experience to make derived decisions. This is where the financial applications of these chips comes in. Who knows if a machine with this chip can make better decisions than us on investing?

      To Hawkins conjecture, if this chip is built within a machine, equipped with our 5 senses, it should be self-teaching and able to adapt to its environment, therefore with the ability to make reasonable decisions. Helen Keller only had 3 senses and she was able to adapt to this world. I can see endless possibilities for applications of these chips?
      Bengia
    • RE: IBM creates cognitive semiconductors: A step toward right brain computers

      @jgm@... It looks shocking like the neural net chip in terminator 2.
      Eman101
  • RE: IBM creates cognitive semiconductors: A step toward right brain computers

    skynet
    PaulTraite
  • RE: IBM creates cognitive semiconductors: A step toward right brain computers

    Mister Luddite Person reminds me that there are still people who have not been rendered unemployed by automation.
    Robert Hahn
  • RE: IBM creates cognitive semiconductors: A step toward right brain compute

    It looks like we are on our way to either, a Terminator Apocalypse or the Matrix, and becoming Duracell batteries.

    J/K
    jpathawk
  • RE: IBM creates cognitive semiconductors: A step toward right brain computers

    Skynet?! Don't think so. Neural networks aren't new. New is only fitting them in small, fast chips. Will it give self-awareness to computers? Yep, sure, exactly in the same way as linking computers by internet gave them super powers and they rule whole world already ;)
    yellow1pl
  • RE: IBM creates cognitive semiconductors: A step toward right brain computers

    As is so often the case in these conversations we already have the arguments from the extreme: "Apocalypse" or "Luddite Fools." However, let's not dismiss the fringe out of hand.

    Frankly, there has been an open debate (within the CompSci and Philosophy camps) for decades on whether computers will ever reach sentience. Some very learned folks argue (essentially) that there is something special about humans that no amount of tinkering on our part will be able to replicate. Others see that line of reasoning as preposterous. Surely the magic of thought, given enough time, might be attainable by our creations. Heck, a half century ago Alan Turing proposed a test whereby we might judge such claims.

    The question is not whether this new chip means sentient computers have arrived (surely not!), but if it moves us closer down that path. Of course, Prof. Searle and others would say that path will never, could never, lead to machine thought anything like ours.

    Do we need to be afraid? Not yet, to be sure, and possibly never. Do we need to consider the implications of sentient machines? Perhaps. Will we? Probably not, but to dismiss the Skynet references as those of Luddites misses the mark.

    What's clear, however, is that this is a great step forward and another feather in IBM's cap.
    DAJCHudson