Moving AI to the Edge...

“There are an estimated 3 billion smartphones in the world, and 7 billion connected devices," Googlers Alex Ingerman and Krzys Ostrowski waxed lyrically. "These phones and devices are constantly generating new data ... Wouldn’t it be better if we could run the data analysis and machine learning right on the devices where that data is generated, and still be able to aggregate together what’s been learned?”

https://www.tensorflow.org/federated/

TensorFlow Federated (TFF) is an open-source framework for machine learning and other computations on decentralized data. TFF has been developed to facilitate open research and experimentation with Federated Learning (FL), an approach to machine learning where a shared global model is trained across many participating clients that keep their training data locally. For example, FL has been used to train prediction models for mobile keyboards without uploading sensitive typing data to servers.

TFF enables developers to simulate the included federated learning algorithms on their models and data, as well as to experiment with novel algorithms. The building blocks provided by TFF can also be used to implement non-learning computations, such as aggregated analytics over decentralized data. TFF’s interfaces are organized in two layers.

TFF enables developers to declaratively express federated computations, so they could be deployed to diverse runtime environments. Included with TFF is a single-machine simulation runtime for experiments. Please visit the tutorials and try it out yourself!

CHECK IT OUT HERE:

https://coral.withgoogle.com/