Power Talk: Performing Machine Learning in Few KBs of RAM

Nov 14, 2019


Auditorium 1

45 minutes

Machine Learning

Several critical applications require ML inference on resource-constrained devices, especially in the domain of the Internet of Things like smart city, smart house, 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.


Key Takeaways:

If you want to learn how to make tiny devices with low memory around you intelligent, then come attend this talk!


Check out the below video to know more about the talk.


  • Prateek Jain

    Senior Principal Researcher


Copyright 2019 Analytics Vidhya. All rights reserved