Song Han is an assistant professor at MIT EECS. Dr. Han’s research focuses on efficient deep learning computing. He proposed “Deep Compression” that can compress neural networks by an order of magnitude, and the hardware implementation “Efficient Inference Engine” that brings compressed weights and sparsity into deep learning accelerators. His work received the best paper award in ICLR’16 and FPGA’17; He is the recipient of 35 Innovators Under 35 (TR35) and NSF CAREER Award. The pruning, compression and acceleration techniques have been integrated into many AI chip products in industry. His hobbies include biking, snowboarding, drum sets, and design.