By 2025, it is estimated that there will be 21 Billion IoT devices in the entire world. With the advancement of artificial intelligence and IoT, there will be a huge demand of Machine Learning and Deep Learning applications at Edge or Node devices. So the question is, how exactly can we perform real-time machine learning on the edge? 

In this session, we will take a tour of suite of approaches powered by Tensorflow, that can help us to develop real-time machine learning and deep learning operations on edge devices!

Key Takeaways:

1. Training and inferencing of ML and DL models on client browsers and edge devices using Tensor.js and Node.js
2. Using Tensorflow lite for training and deployment ML and DL models on light-weight edge devices like Raspberry Pi.
3. TensorHub for registering and versioning trained models that can be deployed on edge devices.
4. Case-studies where real-time model training and inferencing are required for light-weight edge devices.