An introduction to machine learning with application. The course covers the fundamentals of classification and regression, as well as, the methodology behind the design and implementing various models. Students will be introduced to a variety of topics including parameter estimation, model training/fitting, goodness of fit, generalization, regularization, inference, and objective & loss functions. Along the way, students will learn practical tools for building machine learning models, applications of machine learning, and related mathematics.
The goal of this course is to provide you with the foundational knowledge of machine learning and its applications. To achieve this goal, you will study the underlying mathematics, statistics, and algorithms to used to create machine learning models. You will learn to appropriately apply these methods to solve complex, real-world problems.
The course will include regular homework and/or programming assignments. Unless otherwise specified, assignments are due before the beginning of class on the due date. There will be no credit given for late assignments (without an excused absence)—turn in as much as you can.
Reading assignments should be completed before the lecture covering the material. Not all reading material will be covered in the lectures, but you will be responsible for the material on homework and exams. Quizzes over the assigned reading may be given at any time.
See the GFU CS/IS/Cyber policies for collaboration and discussion of collaboration and academic integrity. Most students would be surprised at how easy it is to detect collaboration in programming—please do not test us! Remember: you always have willing and legal collaborators in the faculty.
Almost all of life is filled with collaboration (i.e., people working together). Yet in our academic system, we artificially limit collaboration. These limits are designed to force you to learn fundamental principles and build specific skills. It is very artificial, and you'll find that collaboration is a valuable skill in the working world. While some of you may be tempted to collaborate too much, others will collaborate too little. When appropriate, it's a good idea to make use of others—the purpose here is to learn. Be sure to make the most of this opportunity but do it earnestly and with integrity.
All students in the College of Engineering are required to create and maintain an online portfolio on Portfolium to showcase their best work. Portfolium is a "cloud-based platform that empowers students with lifelong opportunities to capture, curate, and convert skills into job offers, while giving learning institutions and employers the tools they need to assess competencies and recruit talent."
Students will post portions of their coursework to Portfolium as directed by their instructor. For example, a portfolio entry might be PDF of poster or presentation content, screenshots or a video demonstration of a software or hardware project, or even an entire source code repository. In addition to required portfolio entries, students are encouraged to post selected work to their portfolios throughout the year.
Students will work with their faculty advisor to curate and refine their portfolios as they progress through the program. Students shall ensure that all portfolio entries are appropriate for public disclosure (i.e., they do not reveal key components of assignment solutions to current or future students).
If you have specific physical, psychiatric, or learning disabilities and require accommodations, please contact the Disability Services Office as early as possible so that your learning needs can be appropriately met. For more information, go to ds.georgefox.edu or contact Rick Muthiah, Director of Learning Support Services (503-554-2314 or firstname.lastname@example.org).
The Academic Resource Center (ARC) on the Newberg campus provides all students with free writing consultation, academic coaching, and learning strategies (e.g., techniques to improve reading, note-taking, study, time management). The ARC, located in the Murdock Learning Resource Center (library), is open from 1:00–10:00 p.m., Monday through Thursday, and 12:00–4:00 p.m. on Friday. To schedule an appointment, go to the online schedule at arcschedule.georgefox.edu, call 503-554-2327, email email@example.com, or stop by the ARC. Visit arc.georgefox.edu for information about ARC Consultants' areas of study, instructions for scheduling an appointment, learning tips, and a list of other tutoring options on campus.
At any point in the term, you can leave anonymous feedback via this form. If there is something you want or need to tell me about the course feel free to leave a comment.
Computer science and engineering are professional programs which aim to produce responsible, respectful individuals who are prepared for the workplace. Hence, there are some standards of student classroom behavior. It is your responsibility to monitor your own behavior and act appropriately, failure to do so will result in a penalty to your grade. The following are expected of students.
The final course grade will be based on:
Week 1 – 2
Supervised Learning, Loss Functions, & Linear Regression
Reading: 2.1–2.3, 9.2, & 11.1–11.4
Week 3 – 4
Classification, Probability, & Naive Bayes
Reading: 24.1–24.2, & 24.5
Discriminative models, separability, overfitting, Perceptron, & Logistic Regression
Reading: 9.3, 14.1–14.5, 17.1–17.2
Linear Algebra & Neural Networks
Reading: Appendix C, 20.1–20.7
Deep Learning & Computer Vision
Reconstruction models & Introduction to Natural Language Processing
Reading: 22.1 – 22.2
This page was last modified on 2019-09-19 at 13:39:53.
George Fox University · 414 N Meridian St · Newberg, Oregon 97132 · 503-538-8383
Copyright © 2018–2020 George Fox University. All rights reserved.