ML-NET

The goal of this 45h-course is to understand the basics of Machine Learning and apply it to problems in Computer Networks.

Equal space is given to theory and practice.

Lectures (notation used):

  1. Introduction: slides; video; code
  2. Regression: slides; video; code
  3. Regression (continued) and Classification: slides video ; code
  4. Neural Networks slides video; code
  5. Trees and Ensembles slides video; code
  6. Unsupervised Learning: Clustering and Anomaly Detection slides video; code
  7. Dimensionality reduction for Anomaly Detection and Supervised Learning code

Lectures provided by external experts

  • Dimensionlity Reduction and Network Anomalies
  • Machine Data Analysis with Elastic Stack
  • Precictive Maintenance
  • Machine Learning for High Speed Networks
  • Collecting and processing Network Data
  • Intrusion Detection from Network Traces
  • QoE inference for Video on Demand

Lectures skipped this year:

Python code

  • Python notebooks, ready to run on Google Colab can be found in my github page.
  • All you need is any browser and a google drive account.

English -> French ML dictionary: here

All the material, the code and the slides, are licensed under the Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) License (see the terms): you are free to re-use them, but you must cite the autor and this original work.