Using Federated Learning for Data-privacy in AI Models
This course is only available as a part of subscription plans.
Training duration : 90 minutes
DIFFICULTY LEVEL: ADVANCED
Understanding what the privacism movement is and why it matters for DS/AI/ML
Comprehending that today’s practice of AI is at odds with that movement and, increasingly, with territorial regulation of data processing and data movement
Understanding the concept of federated learning and acknowledging that is has potential to support tomorrow’s regulated AI as well as the privacism movement
Gaining familiarity with the technical aspects of federated learning for its standard algorithm, federated averaging
Achieving familiarity with a privacy-preserving version of federated learning, the open-source framework https://github.com/XayNetwork/XayNet
Understanding why/how the XayNet framework preserves privacy as well as the utility of vertical or horizontal AI use cases
Becoming familiar with the usage of the XayNet framework for a “hello world” AI use case in a tutorial demo session, including installation, configuration, and execution.
INTERESTED IN MORE HANDS-ON TRAINING SESSIONS?
Instructor Bio:
Michael Huth, PhD
Module 1: What is federated learning and why does it matter?
-Strategic context (e.g. AI on the edge and upcoming regulation of AI), technical background (e.g. the federated averaging algorithm), and legal background (e.g. basic principles of data privacy common to EU GDPR and CCPA).
- Discussion of the familiar trade-off between privacy and utility in AI use cases, and show that federated learning can resolve this dilemma (e.g. with experimental evidence on a standard voice recognition benchmark)
- Develop an approach to federated learning that not only resolves the above dilemma but also complies with regulation around data privacy: the open-source framework XayNet.
-XayNet discussion focusing on how its protocol for federated learning preserves privacy (in the legal sense) without compromising the ability for scalable performance.
Module 2: How to use the open-source XayNet for federated learning.
- Hands-on demo to use the framework, how it can be configured for a “hello world” AI use case
- What UI support there is for running and monitoring the execution of this federated learning use case
This course is for current and aspiring Data Scientists, Machine Learning Engineers, AI Product Managers
Knowledge of following tools and concepts is useful:
Learners should have some familiarity with machine learning and its algorithms but neither prior knowledge about federated learning nor of its potential value and technical issues
Some familiarity with programming languages
The replication of the demo in this course will require a stable tool chain for the programming language Rust, and standard tools for installation and editing to build own use-case.
CHECK OUT NEW AND FEATURED COURSES
Instructor Bio: