Resource Efficient ML in 2KB of RAM
Several critical applications require ML inference on resource-constrained devices, especially in the domain of Internet of Things like smartcity, smarthouse etc. Furthermore, many of these problems reduce to time-series classification. Unfortunately, existing techniques for time-series classification like recurrent neural networks are very difficult to deploy on the tiny devices due to computation and memory bottleneck. In this talk, we will discuss two new methods FastGRNN and EMI-RNN that can enable time-series inference on devices as small as Arduino Uno that have 2KB of RAM. Our methods can provide as much as 70x speed-up and compression over state-of-the-art methods like LSTM, GRU, while also providing strong theoretical guarantees.
This talk is based on joint works with Manik Varma, Harsha Simhadri, Kush Bhatia, Don Dennis, Ashish Kumar, Aditya Kusupati, Manish Singh, and Shishir Patil.
About the speaker
Prateek Jain is a senior researcher at Microsoft Research India. He is also an adjunct faculty member at the Computer Science department at IIT Kanpur. He received his PhD in Computer Science from University of Texas at Austin and his B.Tech. in Computer Science from IIT Kanpur. His research interests are in resource-constrained machine learning, high-dimensional statistics, and non-convex optimization. He is also interested in applications of machine learning to privacy, computer vision, text mining and natural language processing. He has served on several senior program committees for top ML conferences and also won ICML-2007, CVPR-2008 best student paper awards.