Machine Learning


CS 578

 Fall 2015


    Instructor Dan Goldwasser

Course Information

    Office: Lawson 2142A

Fall 2015



    Office Hours: Wednesday 11:30-12:30

      (by appointment, at least an hour before)

Tuesday, Thursday 3:00-4:15 Seng-Liang Wang Hall 2599

        Piazza  (Sign up!)






 TA: Xiao (Cosmo) Zhang

       TA: Jihwan Lee


Office:   Haas G18

              Office: 2149 #10






Office Hours:Monday 2:00-4:00

       Office hours: Wednesday 10:00-12:00





Course Description                                                                                                                            


Machine learning offers a new paradigm of computing – computer systems that can learn to perform tasks by finding patterns in data, rather than by running code specifically written to accomplish the task by a human programmer.  The most common machine-learning scenario requires a human teacher to annotate data (identify relevant phenomenon that occurs in the data), and use a machine-learning algorithm to generalize from these examples.  Generalization is at the heart of machine learning – how can the machine go beyond the provided set of examples and make predictions about new data. In this class we will look into different machine learning scenarios (supervised and unsupervised), look into several algorithms analyze their performance and learn the theory behind them.





This class requires some mathematical background. Its not a math class, however you should be comfortable with linear algebra, calculus and probability theory.  Programming knowledge is also required. We will have several machine problems and a final project, all will require hacking skills.




We will cover a lot of material in this class! To keep up I expect you to attend classes (or watch the videos), read and explore the material independently and complete the homework assignments.  

In the first half of the class we will discuss classification in a supervised settings, which will include learning algorithms, basic optimization techniques and machine learning theory. We will then move to advanced topics such as deep learning, probabilistic graphical models and unsupervised learning.  A list of topics (subject to change):

      Decision Trees

      Online Learning

      Logistic regression and SVM

      Machine Learning Theory

      Ensemble methods

      Neural Networks

      Introduction to Probabilistic Graphical Models




      Final exam: 25%

      Mid-Term: 25%

      Homework: 25%

      Final Project: 20%

      Attendance and Participation: 5%  (both in class and on Piazza)


Your assignment can only be submitted electronically by the midnight of the due date. 


Late Submission Policy: you lose 10% of the grade for every 24 hours, for the first 48 hours. After that you will not be able to submit.


Teamwork: Allowed, but each student should submit their own work.




Reading Materials and Text Book


There is no official text book for this class. I will post slides and pointers to reading materials. Recommended books for further reading include:


      Foundations of Machine Learning. Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar (ISBN 026201825)

      Pattern Recognition and Machine Learning. Chris Bishop. (ISBN 0387310738)

      Machine Learning. Tom Mitchell (ISBN 0070428077)

      Understanding Machine Learning: From Theory to Algorithms. Shai Shalev-Shwartz and Shai Ben-David (ISBN  1107057132)


Other Policies


      No cheating. Seriously.

      Questions? Show up for office hours, or email. Check the Piazza site for this class. I will post the questions I get (and answers).


More Policies