Deep Learning in Production
Deep learning algorithms are now transiting from proof-of-concepts or academic research to production deployments in industry. In this talk, we discuss lessons learned in engineering algorithms at scale, from model development to inference optimizations to performance monitoring in the field. We also present the Intel Nervana portfolio of software and hardware to enable faster deployments.
Hanlin is an engineering lead at Intel’s AI Products Group. He leads AI projects with federal agencies as well as research initiatives in computer vision. Hanlin joined Intel from its acquisition of the deep learning startup Nervana Systems. At Nervana and now Intel, Hanlin co-developed the open-source deep learning framework neon, and built algorithms used in applications ranging from satellite imagery analysis to neural spiking predictions. Hanlin obtained his Ph.D. from Harvard University, where he investigated the role of recurrent neural networks in human cortex.