Print this chapterPrint this chapter

UoPeople Online Syllabus Repository (OSR)

MSIT

MSIT 5226: Foundations of Machine Learning

MSIT 5226: Foundations of Machine Learning

Credits: 3

Course Description

This course covers the theory and practical algorithms for machine learning from a variety of perspectives and will introduce the fundamental concepts that enable computers to learn from experience. An emphasis will be placed the practical application to real problems. Topics include classification, clustering, dimension reduction, support vector machines, learning theory, online algorithms, and classical methods such as linear regression and reinforcement learning. This course will also offer a mathematical and practical perspective on artificial neural networks and will investigate the optimization and regularization techniques.

Required Textbook and Materials

UoPeople courses use open educational resources (OER) and other materials specifically donated to the University with free permissions for educational use. Therefore, students are not required to purchase any textbooks or sign up for any websites that have a cost associated with them. The main required textbooks for this course are listed below, and can be readily accessed using the provided links. There may be additional required/recommended readings, supplemental materials, or other resources and websites necessary for lessons; these will be provided for you in the course's General Information and Forums area, and throughout the term via the weekly course Unit areas and the Learning Guides.

Software Requirements/Installation

This course will make use of two different software tools. The first is the R programming language environment and the second is the basic prop neural network simulator.

Learning Objectives and Outcomes

By the end of this course students will be able to:

  1. Analyze the advantages of using Machine Learning techniques in real-world problems.
  2. Examine machine learning algorithms using a mathematical perspective, to solve variant problems.
  3. Compare and contrasts developmental theories to optimize learning.
  4. Develop machine learning algorithms with the ability to use them for a wide range of problems.

Course Schedule and Topics

This course will cover the following topics in eight learning sessions, with one Unit per week.

Course Schedule and Topics
Week Unit Topic
1 1 Introduction to Machine Learning
2 2 The PAC Learning Framework
3 3 Support Machine Vectors
4 4 Kernel Methods
5 5 Online Learning
6 6 Multi-Class Classification
7 7 Algorithmic Stability and Dimensionality Reduction
8 8 Reinforcement Learning

Learning Guide

This course will cover the following topics in eight learning sessions, with one Unit per week.

Unit 1: Introduction to Machine Learning
  • Introduce yourself in the Course Forum
  • Read the Learning Guide and Reading Assignments
  • Participate in the Discussion Assignment (post, comment, and rate in the Discussion Forum)
  • Complete and submit the Written Assignment
  • Complete the Reflective Portfolio Assignment

Unit 2: The PAC Learning Framework
  • Peer assess Unit 1 Written Assignment
  • Read the Learning Guide and Reading Assignments
  • Participate in the Discussion Assignment (post, comment, and rate in the Discussion Forum)
  • Complete and submit the Written Assignment
  • Complete the Reflective Portfolio Assignment
Unit 3: Support Machine Vectors
  • Peer assess Unit 2 Written Assignment
  • Read the Learning Guide and Reading Assignments
  • Participate in the Discussion Assignment (post, comment, and rate in the Discussion Forum)
  • Complete and submit the Written Assignment
  • Complete the Individual Project Activity and begin research on your assigned topic (Due Unit 7)
  • Complete the Reflective Portfolio Assignment
Unit 4: Kernel Methods
  • Peer assess Unit 3 Written Assignment
  • Read the Learning Guide and Reading Assignments
  • Participate in the Discussion Assignment (post, comment, and rate in the Discussion Forum)
  • Complete and submit the Written Assignment
  • Continue working on the Individual Project
  • Complete the Reflective Portfolio Assignment
Unit 5: Online Learning
  • Peer assess Unit 4 Written Assignment
  • Read the Learning Guide and Reading Assignments
  • Participate in the Discussion Assignment (post, comment, and rate in the Discussion Forum)
  • Continue Working on the Individual Project
  • Complete and submit the Written Assignment
  • Complete the Reflective Portfolio Assignment
Unit 6: Multi-Class Classification
  • Peer assess Unit 5 Written Assignment
  • Read the Learning Guide and Reading Assignments
  • Participate in the Discussion Assignment (post, comment, and rate in the Discussion Forum)
  • Complete and submit the Written Assignment
  • Continue working on the Individual Project
  • Complete the Reflective Portfolio Assignment
Unit 7: Algorithmic Stability and Dimensionality Reduction
  • Peer assess Unit 6 Written Assignment
  • Read the Learning Guide and Reading Assignments
  • Participate in the Discussion Assignment (post, comment, and rate in the Discussion Forum)
  • Complete and submit the Written Assignment
  • Complete and submit the Individual Project
  • Complete the Reflective Portfolio Assignment
Unit 8: Reinforcement Learning
  • Peer assess Unit 7 Written Assignment
  • Read the Learning Guide and Reading Assignments
  • Participate in the Discussion Assignment (post, comment, and rate in the Discussion Forum)
  • Complete the Reflective Portfolio Assignment
  • Complete and submit the anonymous Course Evaluation

Course Requirements

Discussion Assignments & Response Posts/Ratings

Some units in this course require that you complete a Discussion Assignment. You are required to develop and post a substantive response to the Discussion Assignment in the Discussion Forum. A substantive response is one that fully answers the question that has been posted by the instructor. In addition, you must extend the discussion by responding to at least three (3) of your peers’ postings in the Discussion Forum and by rating their posts. Instructions for proper posting and rating (out of a 10 point scale) are provided inside the Discussion Forum for each week. Discussion Forums are only active for each current and relevant learning week, so it is not possible to contribute to the forum once the learning week has come to an end. Failure to participate in the Discussion Assignment by posting in the Discussion Forum and responding to peers as required may result in failure of the course.

Written Assignments

Most units in this course require that you complete a Written Assignment, which may come in many forms (case study, research paper, etc.). You are required to submit your assignments by the indicated deadlines and, in addition, to peer assess three (3) of your classmates’ assignments according to the instructions found in the Assessment Form, which is provided to you during the following week. During this peer assessment period, you are expected to provide details in the feedback section of the Assessment Form, indicating why you awarded the grade that you did to your peer. Please note that each assignment grade is comprised of a combination of your submission (90%) and your peer assessments (10%). Failure to submit Written Assignments and/or Assessment Forms may result in failure of the course.

Group Activities

During this course, you will be required to complete work as part of a small group. Group work is an important component of your coursework, as it allows you to deepen relationships with classmates, and gain a more thorough understanding of the topics presented in this course. Further, group work mimics the business environment in which projects are often conducted in small teams across different departments. You will be randomly assigned to your groups and are expected to work with your teammates throughout the term for all group activities.

Reflective Portfolio Activities

Portfolio Activities are tools for self-reflection and evaluation within the context of the course. These activities are designed as a means to document and critically reflect upon your learning process. Activities you develop for this course will be kept in your Research and Practice Portfolio and will be important as you progress towards the final courses in your program, particularly the Advanced Practice and Capstone courses. Ideally, you will draw from your coursework and experiences, as well as what you’ve learned in other courses, and your own current teaching practice to showcase your overall growth and examine ways in which you can continue to develop and sharpen your research interests and expand your cadre of instructional methods.

Course Forum

The Course Forum is the place to raise issues and questions relating to the course. It is regularly monitored by the instructors and is a good place to meet fellow students taking the same course. While it is not required to participate in the Course Forum, it is highly recommended.

Course Policies

Grading Components and Weights

Each graded component of the course will contribute some percentage to the final grading scale, as indicated below:

Grade Components
Course Requirements Percentage
Discussion Assignments 20%
Written Assignments
 30%
Individual Project
 25%
Reflective Portfolio Activities 25%
Total 100%

Grading Scale

This course will follow the standard 100-point grading scale defined by the University of the People, as indicated below:

Grading Scale
Letter Grade Grade Scale Grade Points
A+ 98 - 100
 4.00
A  93 - 97
 4.00
A- 90 - 92
 3.67
B+ 88 - 89
 3.33
B  83 - 87
 3.00
B- 80 - 82
 2.67
C+ 78 - 79
 2.33
C 
 73 - 77
 2.00
C-
 70 - 72
 0.00
D+
 68 - 69
 0.00
D 
63 - 67
 0.00
D-
 60 - 62
 0.00
F 
Under 60
 0.00
 CR  N/A  N/A
 NC  N/A  N/A
 NF  N/A  N/A
 W  N/A  N/A
Grade Appeal

If you believe that the final grade you received for a course is erroneous, unjust, or unfair, please contact your course instructor. This must be done within seven days of the posted final grade. For more information on this topic, please review the Grade Appeal Procedure in the University Catalog.

Participation

Non-participation is characterized by lack of any assignment submissions, inadequate contributions to the Discussion Forums, and/or lack of peer feedback to Discussion/Written Assignments. Also, please note the following important points about course participation:

  • Assignments must be submitted on or before the specified deadline. A course timeline is provided in the course schedule, and the instructor will specify deadlines for each assignment.
  • Any student showing non-participation for two weeks (consecutive or non-consecutive) is likely to automatically fail the course.
  • Occasionally there may be a legitimate reason for submitting an assignment late. Most of the time, late assignments will not be accepted and there will be no make-up assignments.
  • All students are obligated to inform their instructor in advance of any known absences which may result in their non-participation.
Academic Honesty and Integrity

When you submit any work that requires research and writing, it is essential to cite and reference all source material. Failure to properly acknowledge your sources is known as “plagiarism” – which is effectively passing off an individual’s words or ideas as your own. University of the People adheres to a strict policy of academic honesty and integrity. Failure to comply with these guidelines may result in sanctions by the University, including dismissal from the University or course failure. For more information on this topic, please review the Academic Integrity Policy in the University Catalog.

Any materials cited in this course should be referenced using the style guidelines established by the American Psychological Association (APA). The APA format is widely used in colleges and universities across the world and is one of several style and citation formats required for publication in professional and academic journals. Refer to the UoPeople's APA Tutorials in the LRC for help with APA citations.

Code of Conduct

University of the People expects that students conduct themselves in a respectful, collaborative, and honest manner at all times. Harassment, threatening behavior, or deliberate embarrassment of others will not be permitted. Any conduct that interferes with the quality of the educational experience is not allowed and may result in disciplinary action, such as course failure, probation, suspension, or dismissal. For more information on this topic, please review the Code of Conduct Policy in the University Catalog.