Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Syllabus

Course overview

Application of machine learning tools, with an emphasis on solving practical problems. Data cleaning, feature extraction, supervised and unsupervised machine learning, reproducible workflows, and communicating results.

You should be familiar with Python programming. See the course learning objectives for what you will learn.

See the course homepage for class times, locations, instructors, and tutorial details.

Communication and getting help

For questions about course material, post on Ed Discussion or attend office hours.

For administrative questions, extensions, and academic concessions, email course coordinator Carol Feng at cpsc330-admin@cs.ubc.ca. See academic concessions for the request process.

Course materials

See the local setup guide if you want to run notebooks on your own computer.

Lecture recordings

This is an in-person class, and we do not livestream or make recordings available by default. If you miss a class, you can catch up by reviewing the lecture notes and talking to your peers. Students who were absent for approved reasons (e.g., illness, jury duty) can be given access to existing lecture recordings (when available), but please note that these will be from previous course instances. It is the student’s responsibility to make sure they are keeping up with the most up-to-date material, which will be the one included in the notes.

Assessments and grading

See the assessment schedule on the course homepage for homework due dates, the syllabus quiz deadline, and exam dates.

Grade weights

ComponentWeight
Participation5%
Homework15%
Midterm 125%
Midterm 225%
Final30%

Passing requirements

All students must satisfy both conditions to pass the course:

If a student does not satisfy the appropriate requirements, the student will be assigned the lower of their earned course grade or, a maximum overall grade of 45 in the course. In exceptional cases (with approved concessions), passing requirements may be waived at the discretion of the course instructor; if waived, the student will earn a maximum grade of 50% in the course.

See the detailed grade policies for more information.

Participation

Participation is worth 5% of the course grade. We plan to assess participation during tutorials; details on how to earn credit will be announced.

Syllabus quiz

Complete the syllabus quiz by the deadline listed on the course homepage. The quiz is ungraded and does not contribute to your course grade.

Homework

The plan is that most of the assignments will contribute equally towards the overall Assignments grade.

We will drop your lowest homework grade. However, because Homework 5 is a significant, project-like assignment, and it is crucial for students’ preparation, Homework 5 is excluded from the drop grade policy.

See homework submission instructions for more detailed instructions on submitting homework assignments.

Late submissions and tokens

Assignments will be due at 11:59 PM on the due date. If you cannot make this due date, you may use a “late token”. Each student will have 4 late tokens for the entire semester, which we will track. No action is required on your part to use the tokens, just make sure that you have a sufficient number if you are planning on using them.

For example, if an assignment is due on a Monday at 11:59 PM:

There is no penalty for using “late tokens”, but you will get a mark of 0 on an assignment if you:

We will post solutions 48 hours after the due date.

Midterms

There will be midterms in CPSC 330 and they will be conducted in the ORCA via self-reservation over a multi-day period. The ORCA (open resource centre for assessments) is designed to enhance the student’s writing experience by providing them with a familiar, secure testing environment with quick access to technical support, as well as support from their instructor for common access issues.

See exam accommodations for accommodation and booking guidance.

Final exam

The final exam is scheduled for the exam period and is comprehensive, covering the material taught over the course of the semester.

Accommodations and academic concessions

Exam accommodations

Students who are registered with the Centre for Accessibility (CfA) with exam accommodations listed on the ORCA accommodations page will need to write their midterms in the Computer-Based Testing Facility (ORCA).

If you have an accommodation that is not listed on that page, you will write your midterms with the CfA and will need to book a time by their deadline. Please do not book midterms with the CfA if you are expected to write them in the ORCA, as the CfA will cancel the exam booking and ask you to book it yourself with the ORCA. If you have any concerns about your accommodations being met in the ORCA, please reach out to your Accessibility Advisor.

Academic concessions

UBC has a policy on academic concession for cases in which a student may be unable to complete coursework. According to this policy, grounds for academic concession can be illness, conflicting responsibilities, or compassionate grounds. Examples of compassionate grounds, from the above policy, include “a traumatic event experienced by the student, a family member, or a close friend; an act of sexual assault or other sexual misconduct experienced by the student, a family member, or a close friend; a death in the family or of a close friend.”

To request an academic concession, email the course coordinator (cpsc330-admin@cs.ubc.ca) before the assessment due date, copying your section instructor. Submitting a request does not guarantee approval. Additional documentation may be requested. We will review your situation and notify you of the decision and, if approved, the next steps.

Please note that when possible (short term occurrences) tokens should be used as the default concession mechanism for assignments.

Academic integrity and conduct

Plagiarism and unauthorized collaboration

You may discuss concepts and approaches with classmates. Write your own answers and code independently unless you are working together on an official group assignment. Follow any additional collaboration instructions for each assessment.

Academic integrity means acting honestly and responsibly in your academic work. Plagiarism is a form of academic misconduct that occurs when an individual presents the work or ideas of another person as their own without appropriate acknowledgement. Plagiarism and unauthorized collaboration include:

Plagiarism is a serious form of academic misconduct and may result in academic consequences, including failing the course. Students are responsible for ensuring that their submitted work does not constitute plagiarism. If you are unsure whether something constitutes plagiarism, consult your instructor before submitting the work.

For more information, see the UBC Academic Misconduct policies.

Use of generative AI (GenAI)

Generative AI tools are increasingly part of professional data science workflows, and students are encouraged to learn how to use these tools effectively and responsibly. Unless otherwise specified by the instructor or assessment instructions, the use of GenAI tools is permitted in your coursework.

However, you are responsible for the accuracy, quality, and understanding of everything you submit, regardless of whether or how GenAI tools were used. You should be able to explain the reasoning, code, analysis, and decisions represented in your submitted work.

Instructors may ask you to explain, defend, reproduce, or extend any part of your submitted work, either in writing or orally. This may include explaining code, justifying methodological choices, interpreting results, identifying limitations, or completing a related task without assistance. An inability to demonstrate sufficient understanding of submitted work may affect the grade for the assessment and, where appropriate, may raise concerns about academic integrity. Difficulty explaining submitted work does not, by itself, establish academic misconduct.

GenAI is not permitted during exams or other timed assessments unless the instructor explicitly allows it. Follow any additional restrictions communicated by the instructor or assessment instructions.

When GenAI use is permitted, name the tool and briefly explain how you used it. Follow any additional disclosure requirements in the assessment instructions.

For group work, all members must know about and agree to any GenAI use. All group members are collectively responsible for the accuracy, quality, and understanding of the submitted work and for complying with any GenAI requirements specified for the assessment.

What you may share with GenAI tools

When GenAI use is permitted, you may ask conceptual questions or share your own code and writing for feedback or debugging, subject to the privacy and group-work requirements in this policy. Do not include instructor-provided assignment instructions, slides, notes, solutions, or quiz and exam questions or answers unless the instructor explicitly permits it.

Many GenAI tools may store or reuse information provided to them. Do not enter confidential or sensitive information into GenAI tools, including student information (names, student numbers, or other personal information), confidential partner or project information (datasets, proprietary information, or client details), or other confidential assessment content.

For additional guidance, see UBC’s approach to generative artificial intelligence tools in teaching and learning.

Collaboration, course materials, and classroom conduct

Registration and prerequisites

Waitlists and registration deadline

CPSC 330 is a very fast-paced course and students who register in the course late have a tendency to struggle greatly and are rarely able to catch-up. In 2026W1, we are expecting that all students registered on open waitlists by 3 PM on Wednesday September 16th will have an opportunity to take the course. If you have been offered a spot in the course, we encourage you to accept (or decline) it as soon as possible so we can clear the waitlists and allow everyone to take the course.

Registration into the course will be closed by the end of the day on Wednesday September 16th, and no further registrations into the course will be permitted. Of course, students will still be able to drop the course until UBC’s official Add/Drop date. We hope this will allow all students to have the best chance at success in this course!

The instructors have no control over the waitlist order and cannot help you bypass the waiting list.

Official prerequisites

The official prerequisites can be found in the course listing. If you do not meet the prerequisites, see prerequisite guidance and rules for prerequisite appeals. We were told that students should not visit the front desk in the CS main office about prerequisite issues, because the folks at the front desk do not have the authority to resolve prerequisite issues.

Auditing

If the course is full, we cannot accommodate official auditors. If there is space and you would like to audit the course, please contact the instructor. All UBC students are welcome to audit the course unofficially.

Land acknowledgement

UBC’s Point Grey Campus is located on the traditional, ancestral, and unceded territory of the xwməθkwəy̓əm (Musqueam) people. The land it is situated on has always been a place of learning for the Musqueam people, who for millennia have passed on their culture, history, and traditions from one generation to the next on this site.

It’s important that this recognition of Musqueam territory and our relationship with the Musqueam people does not appear as just a formality. Take a moment to appreciate the meaning behind the words we use:

TRADITIONAL recognizes lands traditionally used and/or occupied by the Musqueam people or other First Nations in other parts of the country.

ANCESTRAL recognizes land that is handed down from generation to generation.

UNCEDED refers to land that was not turned over to the Crown (government) by a treaty or other agreement.

As you proceed through your journey at UBC, take some time to learn about the history of this land and to honour its original inhabitants.

CPSC 330 Applied Machine Learning 2026W1
CPSC 330 Applied Machine Learning 2026W1
Learning objectives
CPSC 330 vs. CPSC 340