Scholars from the Secure and Private AI Scholarship Challenge by Facebook AI and Udacity working together to implement this tutorial by Daniele Gadler from OpenMined.
We will set up PySyft on two Raspberry Pis and learn how to train a Recurrent Neural Network on a Raspberry Pi via PySyft.
Would you like to learn more about Secure and Private AI? Join this free course from Udacity here
The purpose of using federated learning on a Raspberry Pi (RPI) is to build the model on the device so that data does not have to be moved to a centralized server. In addition to increased privacy, FL works well for Internet-of-Things applications because training can be done on the device instead of having to pass data between devices and a centralized server.
This project, which implements the OpenMined tutorial simulates the process using 2 RPIs to classify a person's surname with its most likely language of origin.
Read more about this here in the article written by Jess
Would you like to know more about to federated learning? Look no further! Our team has prepared a few articles to get you up to speed:
- Federated Learning On Raspberry Pi
- Federated Learning: An Overview
- Article: Federated Learning on Raspberry Pi
All these articles can also be found here in our Wiki section.
Would you like to know what parts are needed and how to get started? Have a look at these articles written by the team:
- A Step by Step guide to installing PyTorch in Raspberry Pi
- Connecting Raspberry Pi to the Internet
- First Steps with your Raspberry Pi
- Federated Learning of a Recurrent Neural Network for text classification, with Raspberry Pis working as remote workers
- Getting started with Raspberry Pi — Install Raspian on your Raspberry Pi using Windows
- Setup guide - What parts are needed for federated learning on Raspberry Pi?
- Project Equipment Setup
- A Step by Step guide to installing PySyft in Raspberry Pi
All these articles can also be found here in our Wiki section.
Do not worry, we have it all covered for you. Head over to the troubleshooting section here
Have a look here to see the implementation of the project in different ways:
- Process to run the project - Elena Kutanov
- Process to run the project - Sergio Valderrama
- PyTorch V1.0.0 Wheel file - Suparna S Nair
- Implementation of the code and guide - Alejandro Ahumada
- Implementation of the code using Nigerian surnames - Temitope Oladokun
- Find the code and dataset for the project here.
- Char RNN Names Classification by Nirupama Sing - Check the slides here
Want a quick guide for the command line commands used? Have a look here.
- Shashi Gharti - https://github.com/shashigharti
- Helena Barmer - https://github.com/helenabarmer
- Jess - https://github.com/jess-s
- Nirupama Singh - https://github.com/nirupamait
- Pooja Vinod - https://github.com/poojavinod100
- Alex Ahumada - https://github.com/projectsperminute
- Elena Kutanov - https://github.com/EVikVik
- Mahmmoud Mahdi (qursaan) - https://github.com/qursaan
- Ayesha Manzur - https://github.com/GlowWorm95
- Ivoline Ngong (Ivy) - https://github.com/ivyclare
- Nachiket - https://github.com/nachiket273
- Joyce Chidiadi - https://github.com/Joycechidi
- Temitope Oladokun - https://github.com/TemitopeOladokun
- Shivam Raisharma - https://github.com/ShivamSRS
- Sankalp Dayal - https://github.com/sankalpdayal5
- Sushil Ghimire
- Juan Carlos Kuri Pinto - https://github.com/jckuri
- cibaca
- Oluwadamilola Saka (Dammy)
- Ebinbin Ajagun - https://github.com/meajagun
- Ankur Bhatia
- Suparna S Nair - https://github.com/suparnasnair
- Sayed Maheen Basheer - https://github.com/SayedMaheen
- Sergio Valderrama - https://github.com/vucket
- Stanislav Ladyzhenskiy - https://github.com/LStan
- Mikaela Sanchez - https://github.com/mikaelasanchez
- Muhammad Naufil - https://github.com/mnauf