ML4CommNets

Machine Learning Methods for Communication Networks and Systems (057368) – PhD Course in Information Technology

Course schedule

Teaching material (Dec. 2021 edition)

1. Intro & ML algorithms
   • Introduction
   • Supervised learning: Linear regression, Logistic regression, ANN, SVM
   • Unsupervised learning: Clustering
   • General concepts
   • Other algorithms
2. Applications of ML
   • Overview of use cases
   • Physical layer domain:
     • QoT estimation
     • Optical Performance Monitoring
     • Optical Power Control
     • Modulation Format recognition
     • Nonlinearity mitigation (not discussed)
   • Network layer domain:
     • Traffic prediction
     • Failure management
     • Traffic classification

Guidelines for final assignment

Suggested readings

• T. Hastie, R. Tibshirani, J. Friedman, “The Elements of Statistical Learning”, (ESL) Ed. Springer
• G. James, D. Witten, T. Hastie, R. Tibshirani, “An Introduction to Statistical Learning with Applications in R”, (ISLR) Ed. Springer
• A collection of papers with communication networks & systems use cases
• Some of my research papers:
  • COMST19 (survey)
  • JLT19 (failure management)
  • TNSM19 (ML in Routing and Wavelength Assignment)
  • ECOC18-1 (traffic prediction), ECOC18-2 (traffic prediction)
  • OFC18 (failure management)
  • INFOCOM19 (traffic prediction)