CSCI 4970/6970-Machine Learning

CSCI 4970/6970-Machine Learning

Spring 2021 - (CRN: 4526/27/28/29)

Instructor Info 

Semih Dinc

Office Hrs: TR 11am - 2pm (Make appointments via https://appoint.ly/t/sdinc)

Zoom: 7058538455 / GH310F

334-244-3251

[email protected]

Course Info

Prerequisite: CSCI 3400 (Minimum Grade of D)

Monday & Wednesday

2:10pm - 3:25pm

Zoom: 7058538455 / GH205

Last Day to Drop the Course: Friday, March 26, 2021

Curtis Course Critique Dates: TBA

IMPORTANT NOTE DUE TO COVID-19 OUTBREAK:

Under AUM’s COVID-19 Campus Health Policy, all students must wear face coverings during most campus activities, including during our in-person class sessions, unless an exemption has been approved by the Dean of Students or the Center for Disability Services.

Students who violate this policy will be asked to leave the classroom to access the lecture/course materials online and may be referred to the Office of the Dean of Students and be subject to discipline policy described in the Student Handbook.

Course Delivery Method

This class has two sections: online and traditional face-to-face (f2f). For students,

1) taking the online section, all class materials will be taught fully online via prerecorded lectures and live Zoom meetings.

2) taking f2f section, I will be following a Blended Flipped Classroom format, due to the COVID-19 restrictions. In this format, I will deliver lectures online in the fifirst class of the week and face-to-face in the second class of the week at the assigned classroom. All lectures will be streamed simultaneously over Zoom.

Syllabus Contingency Plan statement

Should the Alabama Department of Public Health, the Governor, or Chancellor determine the university discontinue f2f instruction in the interest of safety, this course would then move fully online immediately. If normal class and/or lab activities are disrupted due to illness, emergency, or crisis situation (such as a COVID-19 outbreak), the syllabus and other course plans and assignments may be modifified to allow completion of the course. If this occurs, an addendum to your syllabus and/or course assignments will replace the original materials.

Course Objectives

The purpose of this course is to introduce well-know machine learning concepts and methodologies to students. The course aims to provide both theoretical and practical knowledge of learning, including supervised and unsupervised learning, dimensionality reduction, regression, classifification using various methods such as deep learning with artifificial neural networks, decision trees, support vector machines, ensemble methods and more.

Textbook

Required Texts

Andreas C. Müller and Sarah Guido, Introduction to Machine Learning with Python: A Guide for Data Scientists, 1st Edition, (ISBN: 978-1449369415)

Other

Any required (or recommended) reading resources will be provided on Blackboard. 

Grading Scheme

X%              Attendance/Participation

25%            Homework Average (3-4)

20%            Project

25%            Midterm Exam 1 (online)

30%            Final Exam (online)

Grades will follow the standard scale:

A = 89.5-100; B+ = 84.5-89.4; B = 79.5-84.4; C+ = 74.5-79.4; C = 69.5-74.4; D = 60-69.4; F <60.

Course Outcomes

After taking this course, students will have the ability

• to understand broad categorization of learning methodologies,

• to apply supervised, semi-supervised, and unsupervised learning systems,

• to apply dimensionality reduction using feature selection and feature reduction methods,

• to build new learning models for a given problem and train the system,

• to measure the accuracy of a built model with test data,

• to determine which technique is more suitable for a specifific problem.

Blackboard

Homework assignments and all other announcements will be made over BLACKBOARD. Students are expected to access their accounts before the second week of the course.

Homework

Homework will be assigned using Blackboard throughout the term. All assignments are due at midnight on the assigned day. Student submissions should be clear and easily readable by the instructor. Programming assignments are expected to be well written (variable names should be logically consistent) and well documented (comments are necessary for the code blocks). Point deductions may be applied due to lack of organization and documentation.

Late Submission & Make-up Policy

10 points of deduction will be applied for each day of late submission unless there is a reasonable excuse. Make-up option for a missed assignment may be provided if student shows the sufficient enthusiasm and effort to make-up missing assignment.

Exam

The department policies apply to all exams. Makeup exams (quizzes and tests) will be given only if you have made prior arrangements with the instructor, and only if you can provide a valid, documented reason for missing the exam (such as illness or a business trip). If you miss an exam without the prior permission of the instructor, you must provide acceptable documentation to show that you were unable to make advance arrangements.

Attendance and Participation

All students are expected to attend the class. Attendance will be checked throughout the semester. It is strongly encouraged for students to join and contribute the class. Please be respectful in your interaction with the instructor and other fellow students during the lectures. You are not allowed to use your laptop, tablets, smartphones, or other electronic devices for personal reasons (such as playing video games or watching videos) during class. The instructor has the right to ask student to stop using his/her device.

Academic Integrity

Any kind of plagiarism/cheating is subjected to a zero grade for that particular assignment or test. All instances of academic dishonesty will be reported to administrator(s). Please note that discussing about a given homework is allowed as long as the student completes and submits his/her own work. Copying (fully or partially) someone else’s work will be considered as plagiarism.

Complaint Procedure

If you have difficulties or complaints related to this course, your fifirst action should be to discuss these issues with your instructor. If such a discussion would be uncomfortable for you, or fails to resolve your diculties, please contact the chair of the department, Dr. Lei Wu, whose office is located at 310Q Goodwyn Hall.

Disability Accommodations

Students who need accommodations are asked to arrange a meeting during office hours to discuss your accommodations. If you have a conflflict with my office hours, an alternate time can be arranged. To set up this meeting, please contact me by e-mail. If you have not registered for accommodation services through the Center for Disability Services (CDS), but need accommodations, make an appointment with CDS, 147 Taylor Center, or call 334-244-3631 or e-mail CDS at [email protected].

Free Academic Support

All students have the opportunity to receive free academic support at AUM. Visit the Learning Center (LC) in the WASC on second flfloor Library or the Instructional Support Lab (ISL) in 203 Goodwyn Hall. The LC.ISL offers writing consulting as well as tutoring in almost every class through graduate school. The LC may be reached at 244-3470 (call or walk-in for a session), and the ISL may be reached at 244-3265. ISL tutoring is fifirst-come-fifirst served. Current operating hours can be found at www.aum.edu/learningcenter.Tentative Class Schedule