User Tools

Site Tools


syllabus

This is an old revision of the document!


Overview

Description

This course covers fundamental concepts and methods of computational data analysis, including pattern classification, prediction, visualization, and recent topics in deep learning. Students will learn how to

  • read data files of various formats and visualize characteristics of the data,
  • perform statistical analyses on multivariate data,
  • develop and apply pattern classification algorithms to classify multivariate data,
  • develop and apply regression algorithms for finding relationships between data variables,
  • develop and apply reinforcement learning algorithms for learning to control complex systems,
  • write scientific reports on computational machine learning methods, results and conclusions.

For implementations we will be using Python. You may download and install Python on your computer, and work through the on-line tutorials to help prepare for this course. For the written reports, we will be using LaTeX, a document preparation system, freely available on all platforms.

Class meetings will be a combination of lectures by the instructor, discussions of students' questions, and some student presentations in class.

A lot of material will be covered in this course. Students are expected to speak up in class with questions and observations they have about the material. Do not expect to be able to complete all assignments working on your own and without asking any questions. If you find yourself wondering what the next step is in finishing an assignment, please feel free to e-mail the instructor. You may also discuss assignments with other students, but your code and report must be written by you.

You are expected to be familiar with the CS Department policy on cheating and with the CS Department Code of Conduct. This course will adhere to the CSU Academic Integrity Policy and the Student Conduct Code. At a minimum, violations will result in a grading penalty in this course and a report to the Office of Conflict Resolution and Student Conduct Services.

Time and Place

Class meets every Monday, Wednesday and Friday, 9:00 am - 9:50 in Clark Room A103. On-campus and distance-learning students will be able to watch video recordings of lectures.

Prerequisites

CS320 with a grade of C or better.

Textbook

There are no required text books for this course. Readings may be assigned from the following on-line books.

Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville

Reinforcement Learning: An Introduction, by Richard Sutton and Andrew Barto. 2nd edition. On-line and free.

Instructors

Office Hours Contact
Chuck Anderson Computer Science Building (CSB) Room 444 Monday 1-2, Wednesday 2-3 anderson@cs.colostate.edu
970-491-7491
GTA: Jake Lee Room 120
Wednesday 4 - 6 PM
Friday 2 - 4 PM
lemin@cs.colostate.edu

Grading

Your grade for this course will be based only on the assignments, most of which will require the submission of an ipython notebook that includes text descriptions of your methods, results and conclusions and the python code for defining machine learning algorithms, loading data and applying your algorithms to the data. Each notebook will be graded for correct implementation and results, interesting and thorough discussion, and good organization, grammar and spelling. No quizzes or exams will be given.

We plan for five regular assignments during the semester. In total these will count for 80% of your semester grade. The final assignment is a project designed by you and is worth 20% of your semester grade. This 20% will be composed of

  • 2% for the proposal
  • 18% for the written report

The calculation of the final letter grade will be made as follows:

  • A 90 - 100%
  • B 80 - 89.9%
  • C 70 - 79.9%
  • D 60 - 69.9%
  • F below 60%

These ranges for a letter grade might be shifted a little lower, but will not be raised. Late reports will not be accepted, unless you make arrangements with the instructor at least two days before the due date.

syllabus.1481726680.txt.gz · Last modified: 2016/12/14 07:44 by anderson