Description:

How can we build intelligent systems that learn from decentralized data while maintaining privacy? Join us in exploring the powerful PySyft library and its applications in Federated Reinforcement Learning (FRL). In this talk, we’ll dive into the current challenges of data privacy in AI, and how PySyft offers a robust solution for privacy-preserving machine learning. By combining federated learning and reinforcement learning, FRL enables training models across decentralized devices without sharing raw data.

We will discuss real-world problems such as personalized healthcare recommendations, smart home automation, and autonomous vehicles. Discover how FRL can optimize treatment plans based on patient data from multiple hospitals, enhance smart home device behaviors through collaborative learning, and improve autonomous vehicle decision-making by leveraging experiences from multiple vehicles. We'll also provide practical insights into implementing these solutions using PySyft and other relevant tools, and demonstrate how FRL can drive innovation while ensuring data privacy.

By the end of this talk, you will understand how to leverage PySyft for FRL, address real-world privacy concerns, and implement innovative solutions that drive advancements in AI while preserving data privacy. Join us to explore the future of privacy-preserving AI and its transformative impact on various industries.

Prerequisites:

Basics of machine learning and python

Speaker Info:

Shekhar is passionate about Open Source Softwares and active in various Open Source Projects. He has contributed SymPy, Ruby gems like: daru, daru-view (author), Bundler, NumPy & SciPy. He has successfully completed Google Summer of Code 2016, 17, also worked as Admin for SciRuby & mentored. Shekhar was speaker at RubyConf 2018, PyCon 2017, ApacheCon 2020 on “Running ML algorithms with ML tools available in Apache Ecosystem” & “Cluster Management in Apache Ecosystem & Kubernetes”.

Speaker Links:

https://shekharrajak.github.io/