This site may earn affiliate commissions from the links on this page. Terms of use.

truenorth head

IBM and the US Air Force have announced that they're teaming up to build a unique supercomputer based on IBM'south TrueNorth neuromorphic architecture. The new supercomputer will consist of 64 one thousand thousand neurons and 16 billion synapses, while using just 10W of wall power.

Information technology's mutual, when discussing CPUs, to compare them with the human brain. Superficially, the 2 seem similar — brains, similar CPUs, receive inputs, perform calculations based on those inputs, and and then return a upshot. But while brains and conventional CPUs may seem similar at an extremely high level, that similarity disintegrates as soon every bit you start examining either system in any detail.

Transistors are binary (they're either on or off), and they can only modify the behavior of other transistors that they're directly connected to. Neurons, in contrast, take both an analog and a binary attribute. The dendrites — the receiving arms of a neuron — have analog role in that they give a little electrical ripple called a "graded potential" whenever they get a ping from an upstream neuron. If they send enough graded potentials to the cell trunk, the latter and then sends a binary off/on pulse train down the axon. The axon of a nerve sort of "speaks" in binary, fifty-fifty though information technology has to arrange both binary and analog input.

Scientists have spent decades creating software models that more closely resemble the fashion brains process information. Simply there'south an enormous efficiency gap when attempting to simulate something as unlike as a encephalon on mod silicon. While modern CPUs may be millions of times faster at sure calculations than any human being, the human brain's ability efficiency is orders of magnitude ameliorate than the most efficient conventional CPU we tin can build.

IBM'south TrueNorth project is an endeavour to build a neuromorphic, or encephalon-like CPU directly in hardware. The goal is to design superior neural nets and create artificial intelligence in power envelopes that could conceivably operate outside of information centers or stock-still installations.

IBM is claiming that the TrueNorth Neurosynaptic System (that's the official moniker) tin can catechumen and process information from multiple sources in parallel, while simultaneously pairing with more than conventional processors to clarify the information.

The United states Air Force Inquiry Laboratory (AFRL)  was the earliest adopter of TrueNorth for converting data into decisions, said Daniel S. Goddard, director, information directorate, U.Southward. Air Force Research Lab. "The new neurosynaptic system will be used to enable new computing capabilities important to AFRL's mission to explore, paradigm, and demonstrate high-impact, game-changing technologies that enable the Air Strength and the nation to maintain its superior technical advantage," he said in a statement.

The new system will fit in a 4U standard server rack with 512 meg neurons in full per rack. IBM claims this represents an 800-percent annual increase over the last six years, as the first systems contained just 256 neurons.

At present read: How neuromorphic 'encephalon fries' will begin the next era in computing