APL Colloquium

August 20, 2015

Colloquium Topic: IBM TrueNorth: A Low-Power Brain-Inspired Computing Processor and Ecosystem

Drawing on neuroscience, we have developed a parallel, event-driven processor for neurosynaptic computation, that is efficient with respect to logic, memory, and communication. TrueNorth achieves five orders of magnitude reduction in energy-to-solution and two orders of magnitude speed-up in time-to-solution, when running computer vision applications and complex recurrent neural network simulations. Breaking path with the von Neumann architecture, TrueNorth is a 4,096 core, 1 million neuron, and 256 million synapse brain-inspired neurosynaptic processor, that consumes 65mW of power running at real-time. We demonstrate seamless tiling of TrueNorth chips into arrays, forming a foundation for cortex-like scalability. Unprecedented time-to-solution, energy-to-solution, scale, and performance of TrueNorth, combined with underlying flexibility of the kernel enables a broad range of cognitive applications.

Colloquium Speaker: Bryan Jackson

Dr. Bryan L. Jackson is manager of IBM’s Brain Inspired – Hardware group at IBM Research – Almaden. In this role, Dr. Jackson led the team of hardware engineers who designed, built, and tested IBM's largest neuromorphic processor: TrueNorth. TrueNorth can simulate 1 million neurons and 250 million synapses while consuming many orders of magnitudes less power and space than today’s computers. Dr. Jackson joined IBM in 2008 under the DARPA funded SyNAPSE program. His first assignment was to develop nano-scale synaptic technologies for neuromorphic electronics in the Storage Class memory group at Almaden. In 2010, he became a Research Staff Member and Technical Project Manager for hardware design in the Brain Inspired Computing group at Almaden. In 2013, he became manager of the hardware and systems team.  Prior to joining IBM, Dr. Jackson received his PhD from the University of California – Berkeley and holds an Advanced Bachelor of Arts from Occidental College.