SystemX Affiliates: login to view related content.
*To receive email announcements and live stream information for upcoming seminars, please subscribe to the SystemX Seminar/EE310 Mailing list here.
Although today's deep learning networks achieve state of the art accuracy in numerous tasks, they incur exponentially increasing computational complexity and cost. We present novel techniques that achieve over 100X improvements in deep learning performance, while preserving the accuracy of the resulting model. We discuss our recent innovations in AI research, inspired by neocortical structure and function, that enables deep learning networks to outperform standard networks by two-orders of magnitude on existing CPUs, GPUs and FPGAs. We discuss how these techniques can improve throughput, latency, and energy requirements of convolutional and transformer networks. Our techniques can be synergistically combined with other standard optimization techniques to achieve further multiplicative improvements in performance.
Dr. Lawrence Spracklen leads Numenta’s machine learning architecture team, which is focused on the intersection of AI and hardware. Prior to joining Numenta, Lawrence led research and development teams as both CTO and VPE at several other AI startups; RSquared, SupportLogic, Alpine Data and Ayasdi. Before this, Lawrence spent over a decade working at Sun Microsystems, Nvidia and VMware, where he focused on processor design, software performance and scalability. Lawrence holds a Ph.D. in Electronics Engineering from the University of Aberdeen, a B.Sc. in Computational Physics from the University of York and has been issued over 70 US patents.
