Federated Learning: Theory And Practical
Published 10/2024
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 1.52 GB | Duration: 4h 23m
Published 10/2024
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 1.52 GB | Duration: 4h 23m
An Introduction to Federated Learning: Concepts, Implementation, and Privacy Considerations
What you'll learn
Learn the fundamentals and architecture of federated learning
Differentiate between various types of federated learning approaches
Apply federated learning in practical scenarios and combined frameworks
Understand the privacy, security, and communication aspects of federated learning
Requirements
Basic understanding of machine learning concepts and algorithms. Familiarity with Python programming and popular ML libraries (e.g., TensorFlow, PyTorch). No prior knowledge of federated learning is required—this course will cover the essentials.
Description
"Federated Learning: Theory and Practical" is designed to provide you with a comprehensive introduction to one of the most exciting and evolving areas in machine learning—federated learning (FL). In an era where data privacy is becoming increasingly important, FL offers a solution by enabling machine learning models to be trained across decentralized data sources, such as smartphones or local clients, without the need to share sensitive data.This course starts with the basics of machine learning to ensure a solid foundation. You will then dive into the core concepts of federated learning, including the motivations behind its development, the different types (horizontal, vertical, and combined FL), and how it compares to traditional machine learning approaches.By week three, you'll not only grasp the theory but also be ready to implement FL systems from scratch and using popular frameworks like FLOWER. You’ll explore advanced topics such as privacy-enhancing technologies, including differential privacy and homomorphic encryption, and gain insight into practical challenges like client selection and gradient inversion attacks.Whether you are a data scientist, machine learning engineer, or someone curious about privacy-preserving AI, this course offers the theoretical grounding and hands-on skills necessary to navigate the emerging landscape of federated learning.
Overview
Section 1: Week 0: Course Introduction
Lecture 1 Course Intro
Section 2: Week 1: ML Basics
Lecture 2 Machine Learning
Lecture 3 Neural Network Architecture
Lecture 4 NN Model Parameters
Lecture 5 NN Training
Lecture 6 NN Forward Propagation
Lecture 7 NN Loss Computation
Lecture 8 NN Gradient Descent
Lecture 9 NN Backward Propagation
Lecture 10 NN Recap
Lecture 11 NN Scratch Implementation
Lecture 12 NN PyTorch Implementation
Section 3: Week 2: FL Basics
Lecture 13 FL Motivations
Lecture 14 FL Intro
Lecture 15 FL Implementation
Lecture 16 FL Scratch Implementation
Lecture 17 FL FLOWER Implementation
Lecture 18 FL FedAllImplementation
Section 4: Week 3: FL Types
Lecture 19 FL Types Intro
Lecture 20 Horizontal FL
Lecture 21 Vertical FL Intro
Lecture 22 Vertical FL Theory
Lecture 23 Vertical FL Theory Implementation
Lecture 24 Vertical FL Scratch Implementation
Lecture 25 Vertical FL FedAll Implementation
Section 5: Week 4: Combined FL
Lecture 26 FL Combined Scenario 1-Intro
Lecture 27 FL Combined Scenario 1-Theory
Lecture 28 FL Combined Scenario 1-Impl Intro
Lecture 29 FL Combined Scenario 1-Implementation
Lecture 30 FL Combined Scenario 2-Theory
Lecture 31 FL Combined Scenario 2-Impl Intro
Lecture 32 FL Combined Scenario 2-Implementation
Section 6: Week 5: Other Topics in FL
Lecture 33 FL Performance
Lecture 34 FL Performance-Combined
Lecture 35 FL Time
Lecture 36 FL Privacy
Lecture 37 FL Differential Privacy
Lecture 38 FL Homomorphic Encryption
Lecture 39 FL Homomorphic Encryption Implementation
Lecture 40 FL Client Selection
Lecture 41 FL Other Topics
This course is designed for data scientists, machine learning engineers, and AI enthusiasts who want to deepen their understanding of federated learning. It’s also ideal for professionals looking to apply privacy-preserving machine learning techniques in distributed environments. Whether you're familiar with machine learning or new to federated learning, this course offers valuable insights for those interested in practical implementation of FL models.