Home

LECTURES

  1. Lecture (1) — Introduction (Aug 22) [Slides]
  2. Lecture (2) — Probability Review, Likelihood, Parameter Optimization (Aug 27)[Slides + Notebook]
    • Required Reading:
      • Chapter (2) (2.1 – 2.5), Kevin Murphy
      • Chapter (3) (3.1, 3.2.1), Kevin Murphy
  3. Lecture (3) — Maximum Likelihood Estimation, Linear Regression (Aug 29)[Slides + Notebook]
    • Required Reading:
      • Chapter (7) (7.1 – 7.3), Kevin Murphy
  4. Lecture (4) — Linear Regression, Regularization, Ridge Regression  (Sep 5)[Slides + Notebook]
    • Required Reading:
      • Chapter (7) (7.5.1), Kevin Murphy
    • Recommended Reading:
      • Linear Regression using scikit-learn [Notebook]
  5. Lecture (5) — Feature Scaling, Logistic Regression  (Sep 10)[Slides + Notebook]
    • Required Reading:
      • Chapter (8) (8.1 – 8.3.2), Kevin Murphy
  6. Lecture (6) — Regularization in Logistic Regression, Multi-Class Logistic Regression (Sep 19)[Slides + Notebook]
    • Required Reading:
      • Chapter (8) (8.3.6 – 8.3.7), Kevin Murphy
  7. Lecture (7) — BigData and Stochastic Gradient Descent, Generative vs. Discriminative Models (Sep 21)[Slides + Notebook] [Video: Part1, Part2, Part3]
  8. Lecture (8) — Naive Bayes Classifier, Tuning and Evaluating Models (Sep 24)[Slides + Notebook]
    • Required Reading:
      • Chapter (3) (3.5), Kevin Murphy
    • Recommended Reading:
  9. Lecture (9) — Information Theory, Bayesian Networks (Sep 26)[Slides] [Video: Part1, Part2, Part3]
    • Required Reading:
      • Chapter (2) (2.8), Kevin Murphy
      • Chapter (10) (10.1), Kevin Murphy
  10. Lecture (10) — Learning Bayesian Networks (Sep 28)[Slides]
    • Required Reading:
      • Chapter (10) (10.4 – 10.5), Kevin Murphy
  11. Lecture (11) — Unsupervised Learning, Mixture Models, EM Algorithm (Oct 1)[Slides+Notebook]
    • Required Reading:
      • Chapter (11) (11.1 – 11.3), Kevin Murphy
    • Recommended Reading:
      • Gaussian mixture models using scikit-learn [Notebook]
  12. Lecture (12) — Gaussian Mixture Models, EM Algorithm (Oct 3)[Slides+Notebook]
  13. Lecture (13) — Subspace Models, Principal Component Analysis (Oct 8)[Slides+Notebook]
  14. Lecture (14) — Project Proposals Presentations (Oct 10)[Group1] [Group2] [Group3] [Group4] [Group5] [Group6] [Group7] [Group8] [Group9] [Group10]
  15. Lecture (15) — Mid-Term Exam Review(Oct 15) [Slides] [Quiz]
  16. Lecture (16) — Mid-Term Exam(Oct 17)
  17. Lecture (17) — Sparsity, Sparse Linear Regression (Oct 22)[Slides+Notebook]
    • Required Reading:
      • Chapter (13) (13.1 – 13.3), Kevin Murphy
  18. Lecture (18) — Least Angle Regression, Elastic Net (Oct 24)[Slides+Notebook]
    • Required Reading:
      • Chapter (13) (13.4 – 13.5), Kevin Murphy
  19. Lecture (19) — Decision Trees, k-Nearest Neighbor (Oct 29)[Slides]
    • Recommended Reading:
      • Decision Trees and Random Forests using scikit-learn [Notebook]
  20. Lecture (20) — Support Vector Machines, Kernels (Oct 31)[Slides]
  21. Lecture (21) — Neural Networks Representation (Nov 7)[Slides]
  22. Lecture (22) — Neural Networks Learning (Nov 12)[Slides]
  23. Lecture (23) — Backpropagation Examples (Nov 14)[Slides]
  24. Lecture (24) — Convolutional Neural Networks (Nov 19)[Slides]
  25. Lecture (25) — Training Deep Learning Models (Nov 26)[Slides] [Quiz]
  26. Lecture (26) — CNN Architectures (Nov 28)[Slides] [Video: Part1, Part2]
  27. Lecture (27) —  Recurrent Neural Networks (Nov 30)[Slides]
  28. Lecture (28) — Detection and Segmentation (Dec 3)[Slides]
  29. Lecture (29) — Generative Models (Dec 5)[Slides]

ASSIGNMENTS

  1. Assignment (1) — Sentiment Analysis on IMDB Movie Reviews Using Logistic Regression (Sep 12) [Notebook] [Solution]
    • Due Date: Monday, Sep 24
  2. Assignment (2) — Bayesian Network for Instagram Images Classification (Sep 28) [Notebook] [Solution]
    • Due Date: Monday, Oct 8
  3. Assignment (3) — Problem Set (1) (Oct 31) [Problem Set] [Solution]
    • Due Date: Monday, Nov 7 (Before Class Starts)
  4. Assignment (4) — Problem Set (2) (Nov 24) [Problem Set] [Solution]
    • Due Date: Wednesday, Nov 28 (Before Class Starts)
EXAMS

FINAL PROJECT

  • Project Guidelines [Pdf]
  • Project Proposal Template [Latex Template]
    • Due Date: Wednesday, Oct 1
  • Project Progress Report Template  [Latex Template]
    • Due Date: Wednesday, Nov 14
  • Project Poster Template [PowerPoint Template]
    • Due Date: Wednesday, Dec 5
    • Accepted Dimensions: 36 x 48 or 24 x 36 
  • Poster Session on Thursday, Dec 6
    • Sitterson Lower Lobby 10 am – 1 pm
  • Project Report Template  [Latex Template]
    • Due Date: Saturday, Dec 8

Fall 2018 Course Website