Syllabus Overview (Tentative):

WeeksLecturesDateTopicsAssignments, quizzes and project
Weak 113-Jan Introduction (slides)
  • Readings (Murphy): 1.1-1.4
 25-Jan Point estimation (slides)
  • Readings (Murphy): 2.4.1
Weak 2310-Jan Linear regression (slides)
  • Readings (Murphy):
    • Linear Regression Model: 7.1-7.3
    • Error metrics, overfitting, bias-var tradeoff: 6.4
    • Regularization, ridge regression: 7.5.1
    • LASSO: 13.1, 13.3-13.4.1
  • Python Tutorial (link)
 412-Jan Classification, logistic regression (slides)
  • Readings (Murphy): 8.1 - 8.3, 8.5.2
Weak 3517-Jan Online learning: Perceptron (slides)
  • Readings (Murphy): 8.5.0, 8.5.4
Hw1 due
 619-Jan Margin-based approaches: SVM, Kernel Tricks (slides)
  • Readings (Murphy):
    • SVM: 14.5
    • Kernels: 14.4
Weak 4724-Jan Structured models (Naive Bayes) (slides)
  • Readings (Murphy): 3.5
 827-Jan Neural Networks (slides)  
Weak 5931-Jan Neural Networks (slides) Quiz1
 102-Feb Interesting applications (slides) Hw2 due
Weak 6117-Feb Deep Neural models (slides) Project proposal due
 129-Feb Nonlinear models: Decision Trees (slides)  
Weak 71314-Feb Boosting and Ensemble methods (slides) Hw3 due
 1416-Feb Sequential models: HMMs (slides)  
Weak 81521-Feb RNNs (slides) Quiz2
 1623-FebProject proposal - progress report presentationProgress report presentation (3 minutes each)
Weak 91728-Feb Unsupervised models: Clustering (slides) Hw4 due
 182-Mar EM (slides)  
Weak 10197-Mar Reinforcement learning (slides)  
 209-MarPoster presentation + PizzaFinal Project

Text Books:


  • We will have 4 homework assignments, which will be listed below as they are assigned. The assignments will be given out roughly in weeks 2, 4, 6, and 8, and you will have two weeks to complete each one.
  • The assignment should be submitted through Catalyst Dropbox.
  • The EE511 assignments will involve implementing machine learning algorithms or using ML packages with data that we provide. Assignments may be done on your own computer or using the EE Linux Lab. Software provided will require some knowledge of python. Use of other languages is acceptable but won't get TA support. If you choose to use your own computer, you are responsible for installing the requisite open source software.

  • Homework 1: due on Jan 17th, the beginning of the class.
  • Homework 2: due on Feb 2nd, the beginning of the class.

List of Course Projects:

We provide some interesting course projects . But please feel free to come up with your own project idea!

The final project is worth 40% of your grade, which will be split amongst four deliverables (tentative):

Grading (Tentative):

The final grade will consist of 4 homeworks (45%), 2 quiz exams (10%), course project (40%) and course participation (5%).

Course Administration and Policies

  • Assignments will be done individually unless otherwise specified. You may discuss the subject matter with other students in the class, but all final answers must be your own work. You are expected to maintain the utmost level of academic integrity in the course.
  • As we sometimes reuse problem set questions from previous years, please do not to copy, refer to, or look at any solution keys while preparing your answers. Doing so will be regarded as cheating. We expect you to want to learn and not google for answers.
  • Late policy (only applies to assignments and project proposal): Each student has three penalty-free late day for the whole quarter, other than that any late submission will be penalized at a penalty of 10% of the maximum grade per day.
Privacy policy and terms of use