CSCI 447
Machine Learning
Spring 2019
|
CSCI 447 |
| Description: | Introduction to the framework of machine learning from examples, various learning algorithms such as neural networks, and generic learning principles such as inductive bias, Occam's Razor, and data mining. Reviews some statistical learning techniques, but focus is on non-statistical techniques. At the graduate level, students will be required to complete a semester project on a real-life dataset using at least one of, and possibly a combination of, the learning techniques covered during the semester. Students may not take this course for both 400 and 500 level credit. Credits: 3. Prereq, CSCI 332 or consent of instr. Generally offered 2nd semester. |
| Instructor: |
Michele Van Dyne (406) 496-4855 Museum 204B (behind Tami's office and the Network Lab) Office hours: Monday 2:00-3:00, Wednesday and Friday 1:00-2:00 |
| Classes: | MWF | 9:00-9:50am | Lecture | CBB 112 |
| Resources: | Class web page | http://katie.mtech.edu/classes/csci447/ |
| Grades and assignment submission | See Moodle link at top of page, and assignment specific instructions on the Assignments page |
| Grading: | Undergraduate | 2 Midterm Exams: 100 points each | 30% |
| Final Exam (Cumulative): 200 points | 15% | ||
| 7 Assignments | 50% | ||
| Graduate | 2 Midterm Exams: 100 points each | 20% | |
| Final Exam (Cumulative): 200 points | 15% | ||
| 7 Assignments | 35% | ||
| Semester Project | 30% | ||
| Either | Staff discretion (participation and extra-credit) | ±?% |
| Letter Grades: | 93-100% | A |
| 90-92.99% | A- | |
| 88-89.99% | B+ | |
| 83-87.99% | B | |
| 80-82.99% | B- | |
| 78-79.99% | C+ | |
| 73-77.99% | C | |
| 70-72.99% | C- | |
| 68-69.99% | D+ | |
| 63-67.99% | D | |
| 60-62.99% | D- | |
| Below 60% | F |
| Due Dates: | When I do grading, I grade the same question / item across all students, rather than one assignment or exam at a time. This ensures me that I’m being consistent in scoring each item. It also implies that I need to have all student work present while I’m grading. Therefore, the policy is no late homework. Homework assignments will be made available at the start of when that particular topic is to be covered, so there should be no need to wait till the last minute to do it. If there are extenuating circumstances, please let me know. Exams must be taken at the scheduled date and time. Make up exams will not be provided without a very valid reason. See the assignments page for the late policy regarding assignments. |
| Academic honesty: | Cheating will not be tolerated and can result in failure of the course. Submitted programs must be entirely your own work. Under no circumstances should you copy another person's code. Exams are to be strictly your own effort. Unless specified, no electronic devices are allowed in written exams. |
| Communications: | I will use Moodle for posting assignments, grades, and communications. I will also use Tech email for communications, so it's a good idea to check your email. In general, I will try to respond to email or discussion posts within 24 hours, but if you try to contact me on a weekend or holiday, I may not get back to you until the regularly scheduled work week. Finally, note my office hours. These are times I guarantee I'll be in my office, and if you communicate with me during these times, I'll be able to respond more quickly. |
Page last updated: January 08, 2019
