Neurosynaptic supercomputer with 4 billion synapses only needs 2.5 watts of power - Energy equivalent to running a tablet

03/30/2016 - 15:11


Lawrence Livermore National Laboratory (LLNL) has purchased IBM Research’s supercomputing platform for deep-learning inference, based on 16 IBM TrueNorth neurosynaptic computer chips, to explore deep learning algorithms.

IBM says the scalable platform processing power is the equivalent of 16 million artificial “neurons” and 4 billion “synapses.” The brain-like neural-network design of the IBM Neuromorphic System can process complex cognitive tasks such as pattern recognition and integrated sensory processing far more efficiently than conventional chips, says IBM.

READ MORE ON KURZWEIL | AI

READ FURTHER ON IBM | NEWS RELEASES