ECE398BD: Fundamentals of Machine Learning (Lectures)

You can find the typed notes for this class [here]. They will be updated as needed (with a changelog below). The course follows essentially linearly with the notes.

The links to each lecture's in class (handwritten) notes are given below.

Lecture 1 Introduction to the course; Review of linear algebra and probability [notes]
Lecture 2 k-Nearest Neighbor Classifiers and Bayes Classifiers [notes]
Lecture 3 Linear Classifiers and Linear Discriminant Analysis [notes]
Lecture 4 Naive Bayes and Kernel Tricks [notes]
Lecture 5 Logistic Regression, Support Vector Machines and Model Selection [notes]
Lecture 6 K-means Clustering [notes]
Lecture 7 Linear Regression [notes]
Lecture 8 SVD and Eigen-Decomposition [notes]
Lecture 9 Principal Component Analysis [notes]
Lecture 10 Optimization Methods for Machine Learning, Q&A [notes]

Changelog for the Notes

  • February 12, 2017

    • Added a section on Spectral Clustering by request

    • Fixed minor typos

  • February 8, 2017

    • Revised SVM Presentation

    • Added example of bias-variance tradeoff via K-NN Regression

    • Improved LDA example

    • Various other corrections throughout (including to Lect. 5)

  • January 30, 2017

    • Added material on Naive Bayes Classifier

    • Added material on Logistic Regression

    • Corrected typos introduced in last edit in Ch. 6 and various other typos.

  • January 22, 2017

    • Updated Fig. 2.2 with example of 5-NN.

    • Updated Fig. 4.2 to be more legible.

    • Switched to C rather than Σ for covariance matrices, to avoid confusion with summations.

  • January 15, 2017

    • Initial release.