Deep Learning Inference: Optimizations For Wide Scale Deployment

Deep Learning Applications have varied requirements for power, performance, latency, and throughput. This talk will cover Deep Learning inference optimizations for wide scale deployment. The talk will describe both the algorithm techniques as well as hardware specialization for accelerating Deep Neural Network.

Who is this presentation for?
Data Scientists, AI Application developers

Prerequisite knowledge:

What you'll learn?

Rahul Nimaiyar is Director, Machine Learning Solutions at Xilinx. He leads development of Machine Learning solutions including Deep Learning Inference and traditional Machine Learning Inference for Cloud and Data Center. Rahul received his BSEE from Indian Institute of Technology, Kharagpur and earned an MBA from Kellogg School of Management at Northwestern University.