CSCI 4360/6360

All course announcements will be made in the Slack chat.

Lectures are Tuesdays and Thursdays from 11:00am - 12:15pm, and Wednesdays from 11:15am - 12:05pm. All meetings are in Hardman Hall, Room 101.

Course assignments will use AutoLab. We will be using Python 3[.6+] for most assignments.

There are no required textbooks for the course. Course materials will be linked from the lecture schedule and archived in the GitHub repository; other recommended texts will be cited.

You are not expected to know any programming before taking this course, but you are expected to pick it up very quickly.

You are expected to be familiar with probability theory, statistics, and basic machine learning.

Course Details

This is the beating heart of course expectations, policies, and schedules. If something isn't clear, please ask; claiming you didn't know is not an acceptable defense.

• AutoLab

  We are using AutoLab for assignment submission and autograding.

  Take note: AutoLab is run from an internal UGA server, and can therefore only be accessed from campus, or via VPN. AutoLab can be found at this link:

  autolab.cs.uga.edu

• Slack

  Slack is our primary method of communication. The email you receive from me to register on Slack will likely be the last email I will proactively send you. While you are welcome to email me, I receive dozens--sometimes hundreds--of emails each day. Slack cuts through the noise, making it much more likely I will respond to questions in the Slack chat. Plus, in Slack, you have your student colleagues who can probably help even more quickly.

  eds-uga-csci4360.slack.com

• Grading

  There will be five assignments, a required workshop for each student, a midterm exam, and a final project.

  Assignments	45%
  Workshop	10%
  Midterm	20%
  Final Project	25%

  There is NO FINAL EXAM for this class.

• Assignments

  There will be five assignments through the course. Each assignment will be released on Thursday mornings, and will be due by 11:59:59pm two weeks later.

  Assignment are downloaded and submitted through AutoLab. Assignments not submitted through AutoLab will not be graded; do not email me your assignments. For every 24 hours an assignment is late, 25% will be deducted from the final grade.

  Because AutoLab incorporates an auto-grader, you need to follow directions precisely for how you design your code. If the auto-grader fails, it may not necessarily be due to a bug in your code, but rather that you did not adhere to the input/output design guidelines of the assignment.

• Workshops

  Workshops are held most Wednesdays. Each student is required to organize and lead at least one workshop; students can pair up if needed.

  Workshops are meant to be an opportunity to dig into the nuts and bolts of topics we are covering in lecture by demonstrating working code and how these topics can be implemented in practice. This can take several forms--students are encouraged to be imaginative!

  You can demo a new Python package, show a better way of doing something from lecture, or even a live-coding session for how to solve a certain problem (though it should go without saying that you need to practice the live coding ahead of time).

  The current schedule can be found here.

• Midterm

  The midterm exam will be Tuesday, October 3. Expect a mix of multiple choice, short answer, and coding questions.

• Final Project

  The final project is an opportunity for you to really flex your data science skills and tackle a project you're passionate about.

  You are encouraged to form teams of 2 or 3; while teams of 1 person are strongly discouraged, exceptions to the 2-3 person rule of thumb are permitted with justification.

  There are three components: the proposal, the presentation, and the deliverable. The proposal is a 1-2 page roadmap of your project, detailing how you plan to do it, any contingencies and outcomes you can surmise, and your teammates. The presentation is a 30-minute talk summarizing your problem, motivating your approach, and discussing your results. The deliverable is a two-parter: the first is your code, and the second is a 6-10 page NIPS-style paper on your project.

  Graduate students (taking 6360) are required to also submit their papers to a journal or conference; the submission venue must be included in the project proposal. Undergraduate students (taking 4360) can do this for extra credit.

• Final Exam

  There isn't one! Hooray!

• Recommended Textbooks

  The course has no required textbook. However, there are several recommended textbooks that this course will draw on over the semester. Should you want more information on a topic, these would be good places to start.

  Title	Author(s)	Links
  Elements of Statistical Learning	Trevor Hastie, Robert Tibshirani, and Jerome Friedman	[reviews] [amazon] [pdf]
  Statistical Learning with Sparsity	Trevor Hastie, Robert Tibshirani, and Martin Wainwright	[amazon] [pdf]
  Pattern Recognition and Machine Learning	Christopher Bishop	[reviews] [amazon]
  Machine Learning: A Probabilistic Perspective	Kevin Murphy	[amazon]
  Convex Optimization	Stephen Boyd and Lieven Vandenberghe	[amazon] [pdf]
  Computer Vision: Algorithms and Applications	Richard Szeliski	[amazon] [pdf]
  Active Contours	Andrew Blake and Michael Isard	[amazon] [pdf]
  Probabilistic Graphical Models	Daphne Koller and Nir Friedman	[amazon]
  Lecture Notes on Spectral Graph Methods	Michael W. Mahoney	[pdf]
  Statistical Analysis of Network Data	Eric D. Kolaczyk	[amazon]
  Deep Learning	Ian Goodfellow, Yoshua Bengio, and Aaron Courville	[amazon] [html]

• "A Culture of Honesty"

  Here's the short version: don't copy code from the internets or from your friends. Coding is like writing: everyone has their own style, and it's easily recognizable. As such, forgery and plagiarism is also easily sniffed out. Plus, there are tools that do this for us now (this is, after all, a data science class).

  If cheating is uncovered, I am obligated to report the incident, no questions asked.

  The UGA Academic Honesty Policy is the final word on these matters. Lack of knowledge of these policies is not sufficient justification for violations. If in doubt, ask me.

Lecture Schedule

Lectures are held on Tuesdays, Wednesdays, and Thursdays. All lectures are in Hardman Hall, Room 101.

Tues/Thurs lectures are 11:00am - 12:15pm. Wed lectures are 11:15am - 12:05pm.

Contact

The best and most reliable way to reach out to me or the course TA is the course Slack chat.

Mojtaba Fazli (TA)

• Office: Boyd GSRC, Room 537A.
• Office Hours: Fridays, 3:00 - 4:00pm
• Email: mojtaba@uga.edu

Dr. Shannon Quinn (instructor)

• Office: Boyd GSRC, Room 638A.
• Office Hours: Tuesdays, 1:00 - 2:30pm
• Email: squinn@cs.uga.edu
• Phone: 2-4661