Improving prediction accuracy using deep compression and DSD training.
Song Han is a fifth year PhD student with Prof. Bill Dally at Stanford University. His research focuses on energy-efficient deep learning, at the intersection between machine learning and computer architecture. Song proposed Deep Compression that can compress state-of-the art CNNs by 10x–49x and compressed SqueezeNet to only 470KB, which fits fully in on-chip SRAM. He proposed a DSD training flow that improved that accuracy of a wide range of neural networks. He designed EIE: Efficient Inference Engine, a hardware architecture that does inference directly on the compressed sparse neural network model, which is 13x faster and 3000x energy efficient than GPU. His work has been covered by TheNextPlatform, TechEmergence, Embedded Vision and O’Reilly. His work received the Best Paper Award in ICLR’16.