You can download the lecture materials here. We will try to upload lectures prior to their corresponding classes.

  • Scientific computing in Python, foundations of probability theory
    tl;dr: Scientific computing in Python
    [Notebook - Intro Python] [Notebook - foundations of probability theory]

    Suggested readings & references:

  • Class Introduction
    tl;dr: General introduction to the class, scope, organization and evaluation.
    [slides] [survey]

    Suggested readings & references:

    • pdf Nick Bostrom & Eliezer Yudkowsky (2020) The Ethics of Artificial Intelligence
  • Pattern recognition: Introduction
    tl;dr: Introduction, the artificial neuron, basics in probability
    [slides-pattern-recognition-1]

    Suggested readings & references:

    • pdf Russel, S. & Norvig. P. (2020) Artificial Intelligence: a Modern Approach
    • pdf Bishop, C. (2006) Recognition and Machine Learning
  • Make your first ML prediction, the perceptron
    tl;dr: Probability theory, ML prediction
    [Notebook - Make your first ML prediction] [Solution - Make your first ML prediction] [Monolayer perceptron]

    Suggested readings & references:

  • Pattern recognition: The artificial neurone, perceptron (1)
    tl;dr: Linear regression, linear discriminant analysis, decision trees, linear SVM, nearest neighbours, neural nets
    [slides-pattern-recognition-2]

    Suggested readings & references:

  • Pattern recognition: The artificial neurone, perceptron (2)
    tl;dr: Linear regression, linear discriminant analysis, decision trees, linear SVM, nearest neighbours, neural nets
    [slides-pattern-recognition-2]

    Suggested readings & references:

  • Probability, Linear algebra, Calculcus
    tl;dr: Probability theory, ML prediction
    [Notebook - Probability, linear algebra]

    Suggested readings & references:

  • Pattern recognition: The artificial neurone, perceptron (3)
    tl;dr: Linear regression, linear discriminant analysis, decision trees, linear SVM, nearest neighbours, neural nets
    [slides-pattern-recognition-2]

    Suggested readings & references:

  • Pattern recognition: The artificial neurone, perceptron (4)
    tl;dr: Linear regression, linear discriminant analysis, decision trees, linear SVM, nearest neighbours, neural nets
    [slides-pattern-recognition-2]

    Suggested readings & references:

  • Linear classifiers, Perceptron
    tl;dr: Perceptron
    [Notebook - Probability, linear algebra] [Monolayer perceptron]

    Suggested readings & references:

  • Pattern recognition: The artificial neurone, perceptron (5)
    tl;dr: Linear regression, linear discriminant analysis, decision trees, linear SVM, nearest neighbours, neural nets
    [slides-pattern-recognition-2]

    Suggested readings & references:

  • Machine learning pipeline
    tl;dr: Train test split, LDA
    [Monolayer perceptron] [Notebook - assignment_1] [Notebook - assignment_1_solutions]

    Suggested readings & references:

  • Pattern recognition: Ensemble learning, deep nets, SVM (1)
    tl;dr: Ensemble learning, neural nets, SVM
    [slides-pattern-recognition-3]

    Suggested readings & references:

  • Model complexity
    tl;dr: Model selection
    [Model complexity]

    Suggested readings & references:

  • Pattern recognition: Ensemble learning, deep nets, SVM (2)
    tl;dr: Ensemble learning, neural nets, SVM
    [slides-pattern-recognition-3]

    Suggested readings & references:

  • Beyond pattern recognition: similarity scoring
    tl;dr: Face recognition, similarity scoring
    [slides-similarity_scoring]

    Suggested readings & references:

  • Neural nets
    tl;dr: Neural nets
    [Neural nets]

    Suggested readings & references:

  • Unsupervised learning
    tl;dr: Clustering
    [slides-clustering]

    Suggested readings & references:

  • Unsupervised learning: dimension reduction (1)
    tl;dr: dimension reduction
    [slides-dimension_reduction]

    Suggested readings & references:

  • Neural nets
    tl;dr: Neural nets
    [Similarity] [ML for Music]

    Suggested readings & references:

  • Unsupervised learning
    tl;dr: Kmeans
    [Kmeans]

    Suggested readings & references:

  • Unsupervised learning: dimension reduction (2)
    tl;dr: dimension reduction
    [slides-dimension_reduction]

    Suggested readings & references:

  • Graphs
    tl;dr: graphs
    [Learning on graphs]

    Suggested readings & references:

  • Graphs
    tl;dr: Learning on graphs
    [slides-graphs]

    Suggested readings & references:

  • Blind source separation
    tl;dr: ICA
    [ICA notebook] [audio 1] [audio 2]

    Suggested readings & references:

  • Reinforcement learning
    tl;dr: Q-learning
    [slides-Q-learning]

    Suggested readings & references:

  • Q-learning
    tl;dr: Q-learning
    [Q-learning notebook]

    Suggested readings & references: