Federated_Learning_using_Pysyft_Pytorch

Federated Learning

 This is the repository for implementation of federated learning using 
 PyTorch and PySyft. The Skills I learnt from  Secure and Private AI Scholarship course
 offered by Udacity and Facebook.

Objectives

Since Federated learning is an exciting technique to learn on decentralized data so the objective of the reporistory is to introduce federated Learning and to show how it works.

About Federated Learning

Federated learning is a technique where a model can be trained without the need to move and store the training data to a central location.

Image Credits:Google AI blog

Applications of Federated Learning

• This technique is tightly connected to preserve the privacy of users. Many big companies start investing on this powerful technology.
• One of the popular application is Next Word Prediction using federated learning.
• One can use federated learning framework for multi-party database querying without exposing the data.
• Health care is an another domain which is greatly benifiting from this technique

References

• OpenMined Blog: https://blog.openmined.org/upgrade-to-federated-learning-in-10-lines/
• Image Credits: https://1.bp.blogspot.com/-K65Ed68KGXk/WOa9jaRWC6I/AAAAAAAABsM/gglycD_anuQSp-i67fxER1FOlVTulvV2gCLcB/s1600/FederatedLearning_FinalFiles_Flow%2BChart1.png

Acknowledgement

I would like to show my gratitude to Udacity and Facebook for providing me a chance. Three months in this Scholarship Challenge has made huge impact in my life in positive ways. Thank you for helping me to achieve my dreams. Last but not least, I would also like to acknowledge the efforts of slack community who is always ready to help.