Flower: A Friendly Federated Learning Research Framework

Daniel J. Beutel, Taner Topal, Akhil Mathur, Xinchi Qiu, Titouan Parcollet, Nicholas D. Lane arXiv:2007.14390, Jul, 2020 Federated Learning (FL) has emerged as a promising technique for edge devices to collaboratively learn a shared prediction model, while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to store the data in the cloud. However, FL is difficult to implement and deploy in practice...

The Deep (Learning) Transformation of Mobile and Embedded Computing

Dr. Nicholas Lane - University of Cambridge Recorded talk for tinyML Talks local Webcast, September 8, 2020 Mobile and embedded devices increasingly rely on deep neural networks to understand the world -- a formerly impossible feat that would have overwhelmed their system resources just a few years ago. The age of on-device artificial intelligence is upon us; but incredibly, these dramatic changes are just the beginning...(Meetup Announcement)


Xinchi Qiu, Titouan Parcollet, Daniel J. Beutel, Taner Topal, Akhil Mathur, Nicholas D. Lane Coming soon!

Flower: An Open Source Project Guide

Flower is designed to be platform (iOS, Android, Linux and Embedded), framework (TensorFlow, PyTorch, ...) and language agnostic (Python, Java, C++,...). It is an open source project with a full established ecosystem. A Flower Quickstart Guide allows you to setup the federated learning system in less than 50 lines of code. It already provides a number of examples to demonstrate how Flower can be used. Following examples are available: - PyTorch: CIFAR-10 Image Classification - PyTorch: ImageNet-2012 Image Classification - TensorFlow: MNIST Image Classification - Keras: MNIST Image Classification - to be continued Have a look and send us some feedback!