Prerequisite: CS 4412 (formerly CS 3385)
Required text: Machine Learning: An Algorithmic Perspective, 2nd Edition, by Stephen Marsland
Instructor: Paul Bodily (office hours and contact information)
Final grade percentage will be computed as follows:
| Type | Number | Percentage |
|---|---|---|
| Daily Quizzes | 25ish (Drop lowest 3) | 8% |
| Projects | 6 | 44% |
| Homework | 12 | 8% |
| Midterm | 1 | 20% |
| Final | 1 | 20% |
| Course Evaluations | 2 | 1% (extra credit) |
We will have daily quizzes due before the beginning of class. I will drop the lowest 3 quizzes. The quizzes will be on the daily reading assignment. This doesn't mean that you must have a perfect understanding of everything you read. It just means that you need to have a grasp of what is being talked about, why it is important, etc. Quizzes cannot be made up.
Programming projects are done in Java and will be turned in using Moodle. Projects will be in the form of programming and an associated written report. For a number of the machine learning models we study in depth, there will be a programming project involving the implementation of the model and experimentation with its abilities on one or more learning tasks. Much of the learning for this class comes in the development, experimentation, and analysis of the specific models. These programming projects help you gain not only a mastery of the models themselves but also a beginning understanding of the major issues involved in designing machine learning solutions. By the end of the course, you will have developed a suite of machine learning algorithms that will be usable (and useful) in the future. A written report will also be due describing your efforts, results and conclusions. All project specifications and details on what is expected in reports is found via project links under "Assignments" on the Schedule.
We will break into groups of 3-4 people each to do a group project. A month into the semester, we will have you propose real world machine learning projects which could be done in a semester. We will then vote as a class on the projects we feel most appropriate. I will then assign the groups based on your project preferences (as best as I can). Each group will then a) gather and prepare data for the application, b) select machine learning approach(es), c) train the model and gather results, d) consider and implement ways to improve the results, e) write-up the work as a conference style paper and f) give an oral presentation. Details of the report and presentation requirements are provided in the Group Project specification.
Students taking the course for graduate credit are expected to use LaTeX (I suggest using Overleaf) to format all project reports.
Students taking the course for graduate credit will also have a Final Group Project but with some additional requirements. The goal of the CS 5578 Final Project is to provide a structured opportunity for graduate students to incorporate machine learning solutions into a graduate-level research project at ISU. Machine learning is increasingly being incorporated into a variety of disciplines and the skills you gain in this class prepare you well to participate in collaborative, (potentially) cross-discipline research. The project you choose may relate to your graduate research or that of another graduate student in the course. As with the Final Group Project for the CS 4478 students, you should implement and experiment with machine learning model(s) that are appropriate to the project you choose. You are encouraged to work as a group with other CS 5578 students, but you may work alone or with a CS 4478 student (if the latter is willing to agree to the more difficult requirements for the CS 5578 Final Project).
The conference-style report for the CS 5578 Final Group project should include a related works section and compare the performance of the student's implemented model with that of other models (as implemented possibly by third-party software) designed to solve the same task.
CS 5578 students will give an oral presentation with the same requirements as those for the CS 4478 students. Your report and oral presentation should answer the following questions:
To help you understand each basic model that we discuss, there will be a homework for many models and concepts. Each homework assignment is a set up as a self-graded Moodle assignment. You can complete the assignment as many times as is necessary to get 100%. Moodle will record your highest score. You should work out the solution by hand and then use the Moodle form to check your answers. You will be asked to upload your work which can be either a word-processed document or a scan of your handwritten version. It should be neat and legible. The homework is due 10 minutes before the beginning of class on the due date.
There will be one mid-term and one final, both administered via Moodle. They will consist of written problems testing your understanding of the machine learning models and issues covered in class. If you put in the effort on reading, class discussion, and programming projects, then the tests should go well for you. More information can be found in the exam study guide.
Grades are assigned on the following absolute scale:
| 90.0 | <= | A | ||
| 86.0 | <= | A- | < | 90.0 |
| 83.0 | <= | B+ | < | 86.0 |
| 80.0 | <= | B | < | 83.0 |
| 76.0 | <= | B- | < | 80.0 |
| 73.0 | <= | C+ | < | 76.0 |
| 70.0 | <= | C | < | 73.0 |
| 67.0 | <= | C- | < | 70.0 |
| 64.0 | <= | D+ | < | 67.0 |
| 60.0 | <= | D | < | 64.0 |
| 57.0 | <= | D- | < | 60.0 |
| F | < | 57.0 |
An incomplete grade is available when a student who is satisfactorily completing the course and who has completed approximately 70% or more of the course suddenly encounters an extenuating circumstance that prevents them from completing the course. The student must contact me to negotiate the requirements for completing the incomplete grade at the time that the extenuating circumstance arises (not at the end of the semester). For more information see https://coursecat.isu.edu/undergraduate/academicinformation/creditandgradingpolicies/.
In the College of Science & Engineering, a student who earns a failing grade via course work (exams, homework, etc.) and has unexcused absences that total more than 30% of class meetings will receive a grade of "X".
Questions on how to do homework and projects should be asked using the class discord server (link available from Moodle) where other students can benefit from and possibly provide help on your questions in addition to help provided by the professor. Please see section below on "Academic integrity" for clarification on what types of help may or may not be appropriate. Score and grade questions should be addressed directly to the instructor via email.
TA information can be found atop the Moodle page for this course. A tutoring lab is also available for students enrolled in any CS course. Note that not all tutors may have taken the course you need help with, so you may need to try a few different tutors. The schedule and location is available here: https://www.isu.edu/cs/students/cs-tutoring-lab/. Students can also get help from the professor outside of class as needed.
The university also provides more general tutoring services on a variety of subjects (in-person, via Zoom, etc.). Please be sure to check out the University Tutoring website here: https://www.isu.edu/tutoring/.
There is no doubt that knowing when and how to use large language models (LLMs) (e.g., ChatGPT) and other assistive AI will be a valuable asset in your career post-graduation. But you should not be using these tools on any exams, quizzes, or coding projects in your classes as an undergraduate. Your instructors are assuming that the topics that they present and assess you on in your classes are topics that you will have mastered on your own by the time you graduate.
I think of it somewhat like self-driving cars. New drivers are expected to know how to drive a traditional vehicle and to pass all driving tests without any assistance from AI. AI can and does fail. We need drivers who know how to drive without the assistance of AI, who know the rules of the road, who possess an intuition for safety, and who possess the raw skills to drive the car themselves. New drivers would likely be expected to drive a traditional vehicle for the first several years to ensure that this knowledge grabs hold.
In short, I caution you heavily against using LLMs or other assistiveAI in your CS courses. You need to develop the ability to decipher between reputable and non-reputable sources of information, to search Google and find valid answers, to develop ways of knowing, and to develop connections with human experts. You can and should use these tools on your own personal projects. After you have a mastery of the topics you're learning in your class (and on your own personal projects), test ChatGPT (for example) so that you can see for yourself what its strengths and weaknesses are. Avoid the tendency to be overreliant on these tools at the expense of your learning.
Like it or not, much of your future success depends heavily on your skills as a communicator. Whether in project reports or service learning proposals, any work (including emails and forum posts) should exhibit a professional standard of writing. Like it or not, potential and actual employers will judge you based on your ability to communicate. I will happily give feedback on your writing, but it will be of greatest benefit to you if you are making your best effort. Points may be taken off for poor grammar, spelling, etc.
A free writing center is available on both the Pocatello and IF campuses that offers face-to-face, online chat, and online written feedback.
No late homework or projects are accepted. This means that if you turn an assignment in one minute after it is due you will receive a zero. Quizzes and exams cannot be made up. Exceptions are on a case-by-case basis and are only granted for religious holy days (must have prior approval), documented illness, or documented emergencies.
It is in your best interest to submit whatever you can before deadlines. Probably the best way to make sure you are not unpleasantly surprised is to submit incrementally: submit what you have early, and then continue to improve your work and resubmit as you make improvements, up until the deadline.
Note that the schedule is carefully designed to give you plenty of time between when we discuss in class the concepts needed for a project and when it is due. Please start early and make use of that time to do a good job. If you do not get the entire project completed by the deadline, make sure you submit what you have.
In my experience, one key to success, in class, in our profession, and in life in general, is being organized and meeting deadlines. The no-late-work-policy is in large part to help you be successful and be able to continue progressing and focusing on new material. Please submit your work on time!
Not infrequently do students ask me to write them a letter of recommendation. I am generally very happy and willing to do so. I will paint you in the best light possible, but I will be honest and transparent. Make it easy for me to give you a good recommendation:
A letter of recommendation is more than merely a reflection of the grade you receive in the class. It is intended to help future employers/advisors assess how successful you will be as an independent researcher/employee and team member.
For your benefit, I suggest that whenever asking someone to write a letter of recommendation (including myself) that you ask specifically if they are willing and able to write a good recommendation. If they do not feel able to write you a positive recommendation, you do not want them to write you a letter.
You may work together with other members of the class; in fact, you are strongly encouraged to do so; however, do NOT turn in other people's work. There is a fine line that may require some judgment on your part. Unless explicitly stated otherwise, all work is to be done individually. Helping each other through discussion is permitted. You may consult the internet for questions related to programming projects (not homeworks), but you may not copy code from the internet or any other source except for the course textbook. Projects may not be done in groups unless the instructor explicitly says otherwise. Homework may be discussed in groups, but students should be careful to develop individual mastery of the problems and solutions.
Academic integrity is expected of all students. Academic dishonesty, including cheating or plagiarism, is unacceptable. The Idaho State University academic dishonesty policy allows an instructor to impose one of several penalties for cheating that range from a warning up to assigning a failing grade for the course or dismissal from the University. ANY use of an electronic device or other form of unauthorized materials during an exam or other assessment will be considered cheating. For more information, please see the ISU Policies and Procedures Policy 5000 (Student Conduct Code).
Some examples of dishonest behavior include, but are not limited to
I prosecute cheating cases to the full extent. I have a general policy that I adhere to in isolated instances. When addressing academic dishonesty my policy is to submit a report to the registrar's office (two such reports across any courses at ISU can result in expulsion from the university). Besides this report, I give students two choices. The student can simply fail all assignments/exams where academic dishonesty was an issue and then continue to work through the course. The second option is to fail and repeat the course. Simply withdrawing after having been caught for academic dishonesty is not a viable option. If you choose to stay in the course, you will receive a 0 on all assignments where academic honesty was an issue (based on your integrity in letting me know or based on me finding evidence of dishonesty). I do not mean to sound gruff. I do not wish to discourage students from learning, growing, and moving on from such experiences. I will support students however they wish to proceed. Incidents with academic dishonesty do not change my eagerness to support your learning and your success.
To facilitate a productive learning atmosphere, it is expected that students will be punctual, regularly attend class, maintain a positive attitude, use appropriate language, and show respectfulness to other students and the professor. Students are expected to come to class prepared, participate in activities and discussions, and treat others with respect in the classroom, which includes listening interactively to classmates and the professor, and respecting others’ viewpoints. Students should expect frequent and personal invitations to participate in course lectures.
Open laptops and phones are not allowed except for the purpose of taking notes. Please do not text, check social media sites, or eat meals during class.
Students are expected to arrive for class and be in their seats by the scheduled beginning of class. Repeatedly coming to class late disrupts the teaching/learning environment in the classroom and adversely affects the other students in the class.
Our program is committed to all students achieving their potential. If you have a disability or think you have a disability (physical, learning disability, hearing, vision, psychiatric) which may need a reasonable accommodation, please contact Disability Services located in the Rendezvous Complex, Room 125, 208-282-3599 as early as possible.
Success in this course depends heavily on your personal health and wellbeing. Recognize that stress is an expected part of the college experience, and it often can be compounded by unexpected setbacks or life changes outside the classroom. I encourage you to reframe challenges as an unavoidable pathway to success. Reflect on your role in taking care of yourself throughout the term, before the demands of exams and projects reach their peak. Please feel free to reach out to me about any difficulty you may be having that may impact your performance in this course. If you are experiencing stress in other areas of your campus life, I am happy to help you get in contact with other resources on campus that stand ready to assist you. In addition to your academic advisor, I strongly encourage you to contact the many other support services on campus that are available.
ISU Counseling and Testing Services (CATS) would like to remind all students who are enrolled in the current semester (part-time or full-time) they are eligible for free, confidential counseling services. CATS offers individual, group, and couples counseling, as well as Biofeedback Training. We also offers crisis intervention services Monday through Friday from 8-5.
To establish services:
In accordance with Title IX of the Education Amendments of 1972, Idaho State University prohibits unlawful sex discrimination against any participant in its education programs or activities. The university also prohibits sexual harassment—including sexual violence—committed by or against students, university employees, and visitors to campus. As outlined in university policy, sexual harassment, dating violence, domestic violence, sexual assault, and stalking are considered forms of "Sexual Misconduct" prohibited by the university.
University policy requires all university employees in a teaching, managerial, or supervisory role to report all incidents of Sexual Misconduct that come to their attention in any way, including but not limited to face-to-face conversations, a written class assignment or paper, class discussion, email, text, or social media post. Incidents of Sexual Misconduct should be reported to the Title IX Coordinator (visit https://www.isu.edu/aaction/title-ix-notice-of-non-discrimination for contact and other information).
In carrying out its educational mission, Idaho State University is committed to adhering to the values articulated in Idaho State Board of Education Policy III.B. Membership in the academic community imposes on administrators, faculty members, other institutional employees, and students an obligation to respect the dignity of others, to acknowledge the right of others to express differing opinions, and to foster and defend intellectual honesty, freedom of inquiry and instruction, and free expression on and off the campus of an institution.
Many thanks to Dr. Tony Martinez and Mike Brodie for their support and contributions in developing this course.
