Getting AI in Your Pocket with Deep Compression

Deep neural networks (DNNs) have become state-of-the-art for a wide range of applications including computer vision, speech recognition, and robotics. The superior performance often comes at the cost of high computational complexity. The process of creating and training a DNN model is difficult and labor-intense, and the resulting models rarely optimized for running on embedded devices. Automated techniques to improve energy efficiency and speed without sacrificing application accuracy are vital. Companies like Amazon and Facebook showed that compressing weights or squeezing the architecture can reduce the model complexity by a factor of 20-50 while maintaining almost identical performance. The field of 'deep compression' has become a dedicated branch of research. Technical support for such optimizations is starting to be available by a growing set of tools. This talk gives an overview of deep compression techniques and tools with example applications.