FEP3260 Fundamentals of Machine Learning Networks

Basic knowledge of convex optimization and probability theory is required to follow the course. 

• Lecture 1: Introduction
• Lecture 2: Centralized Convex ML  
• Lecture 3: Centralized Nonconvex ML  
• Lecture 4: Distributed ML
• Lecture 5: ADMM, guest lecturer
• Lecture 6: Communication Efficiency
• Lecture 7: Deep Neural Networks
• Lecture 8: Computer Assignment Session and Homework 
• Lecture 9: Special Topic 1: Large-scale ML 
• Lecture 10: Special Topic 2: Security in MLoNs 
• Lecture 11: Special Topic 3: Online MLoNs 
• Lecture 12: Special Topic 4: MLoNs with partial knowledge 
• Lecture 13: Special Topic 5: Application Areas and Open Research Problems

After the course, the student should be able to:

·        give new tools and training to model basic ML problems by optimization

·        present basic theories of large-scale ML, distributed ML, and MLoNs 

·        provide a thorough understanding of how such problems are solved, pros and cons of various approaches, and some experience in solving them

• review on recent topics in ML and MLoNs, including communication-efficiency, security, and MLoNs with partial knowledge
• give students the background and skills required to do research in this growing field