Topic outline

  • Bare Necessities. 

    MS-A0001 - Matrix Algebra. this course explains how to use vectors and matrices to represent data. CS-C3240 will make heavy use of vectors and matrices to represent data and models in machine learning.

    Python Crashcourse by Aalto IT. We will make minimum use of programming concepts, mainly load data from csv files and process it using numeric arrays ("numpy arrays").


    Hands-On.

    CS-EJ3211 - Machine Learning with Python. bachelor level course; covers similar topics as this course but with more emphasis on hands-on skills for implementing ML methods.

    CS-EJ3311 - Deep Learning with Python. bachelor level course; focuses ML methods that use artificial neural networks (see Ch. 3.11 of https://mlbook.cs.aalto.fi) with emphasis on hands-on skills for implementing ML methods.

    Advanced.

    CS-E4710 - Machine Learning: Supervised Methods. master level course; covers similar topics as this course but using more advanced (and powerful) mathematical tools.

    CS-E4830 - Kernel Methods in Machine Learning. master level course; focuses on an important subclass of ML methods that use feature transformations via kernel functions (see Ch. 3.9 and Ch. 9 of https://mlbook.cs.aalto.fi)

    CS-E4890 - Deep Learning. master level course; focuses on an important subclass of ML methods that use artificial neural networks (see Ch. 3.11 of https://mlbook.cs.aalto.fi).

    ELEC-E8125 - Reinforcement learning. master level course; focuses on a subclass of ML methods that must predict optimal actions of an "AI system" that interacts with some environment (e.g., a cleaning robot).

    ELEC-E7261 - Ambient Intelligence (Former ELEC-E7260). master level course; project course focusing on selected advanced ML methods and collaboration in small project teams.