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

  • Overview
    tl;dr: Course overview, syllabus, and introduction to machine learning.
    [notes] [slides]

    Readings:

    • PML: Chapter 1
    • PRML: Chapter 1
  • ML Foundations
    tl;dr: Generalization: overfitting, bias-variance, regularization (L2/L1).
    [notes] [slides]

    Readings:

  • Linear Regression
    tl;dr: Least squares, gradient descent, Ridge and Lasso.
    [notes] [slides]

    Readings:

    • PML: Chapter 11.1-11.4
  • Optimization Basics
    tl;dr: Convexity, stochatsic gradient descent, regularization techniques.
    [notes] [slides] [Matrix Calculus] [Jupyter Notebook]

    Readings:

    • PML: Chapter 8.1, 8.2, 8.4
  • Maximum Likelihood Estimation
    tl;dr: Bernoulli distribution, probability vs likelihood, maximum likelihood.
    [notes] [slides]
  • Logistic Regression
    tl;dr: Logistic regression, linear classifier, softmax.
    [notes] [slides]

    Readings:

    • PML: Chapter 10.1-10.3
  • Support Vector Machines (I)
    tl;dr: Maximum margin classifier, Hard margin SVM.
    [notes] [slides]

    Readings:

    • PML: Chapter 17.3, 8.5
  • Support Vector Machines (II)
    tl;dr: Soft margin SVM, duality, KKT condistions, kernel tricks.
    [notes] [slides]

    Readings:

    • PML: Chapter 17.3, 8.5
  • Decision Trees
    tl;dr: Decision Trees, information gain.
    [slides]

    Readings:

    • PML: Chapter 18.1
  • Midterm Review
    tl;dr: Review of the course material in preparation for the midterm exam.
    [slides]
  • Perceptron + Neural Networks
    tl;dr: Perceptron, neural networks, forward and backward propagation
    [Perceptron] [Neural Networks]

    Readings

    • PML: Chapter 10.2.5
  • Convolutional Neural Networks
    tl;dr: Convolutional Neural Networks, filters, pooling, and applications
    [slides]

    Resources related to PyTorch

    Readings

    • PML: Chapter 14.1-14.3
  • DL Recipe
    tl;dr: Early stopping, ReLU, regularization, optimizers, and dropout.
    [slides]

    Readings

    • PML: Chapter 13.1-13.5
  • Unsupervised Learning
    tl;dr: Unsupervised learning, clustering, and generative modeling.
    [slides]

    Readings

    • PML: Chapter 21.1-21.3
  • Generative Adversarial Networks (GANs)
    tl;dr: GANs, KL divergence, and applications in generative modeling.
    [slides]
  • Autoencoders (AEs)
    tl;dr: Autoencoders, denoising autoencoders and variational autoencoders.
    [slides]
  • Transformers
    tl;dr: Attention, Seq2seq, encoder-decoder architecture, transformer.
    [slides]

    Reading:

  • Final Review
    tl;dr: Final Review
    [slides]