Machine
Learning
CS 578
Fall 2015
Instructor Dan Goldwasser |
Course
Information |
Office: Lawson 2142A |
Fall 2015 |
Phone: Email: dgoldwas@purdue.edu 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 |
|
|
Phone: |
Phone: |
|
|
Email:zhang923@purdue.edu |
Email: jihwan@purdue.edu |
|
|
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.
Prerequisites |
This class requires some mathematical background. ItÕs
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.
Structure |
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):
á Decision Trees
á Online Learning
á Logistic regression and
SVM
á Machine Learning Theory
á Ensemble methods
á Neural Networks
á Introduction to
Probabilistic Graphical Models
Grading |
á Final exam: 25%
á Mid-Term: 25%
á Homework: 25%
á Final Project: 20%
á 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:
á Foundations of Machine
Learning. Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar (ISBN 026201825)
á Pattern Recognition and
Machine Learning. Chris Bishop. (ISBN 0387310738)
á Machine Learning. Tom
Mitchell (ISBN 0070428077)
á Understanding Machine
Learning: From Theory to Algorithms. Shai Shalev-Shwartz and Shai Ben-David
(ISBN 1107057132)
Other Policies |
á No cheating. Seriously.
á Questions? Show up for
office hours, or email. Check the Piazza site for this class. I will post the
questions I get (and answers).