This is the course homepage for CPSC 330: Applied Machine Learning at the University of British Columbia. You are looking at the current version (Jan-Apr 2023). Earlier versions can be found at these links:
- from Sep-Dec 2020 taught by Mike Gelbart
- from Jan-April 2022 taught by Giulia Toti
- from May-June 2022 taught by Mehrdad Oveisi
- from Sep-Dec 2022 taught by Varada Kolhatkar
Instructors: Giulia Toti (201), Mathias Lecuyer (202), Amir Abdi (203)
- Course GitHub page
- Course Jupyter book. Important: this is a static version of the lecture notebooks developed by a previous instructor of the course. It can be used as reference for the content, but not for anything related to the particular course instance (due dates, setup steps, etc.)
- Course videos YouTube channel
- Canvas link
- Syllabus / administrative info
- Piazza (this is where all announcements will be made). Click here to enroll.
- Other course documents
- Past exams
Usually the homework assignments will be due on Mondays and will be released on Tuesdays.
| Assessment | Due date | Where to find? | Where to submit? | Weight (%) |
|---|---|---|---|---|
| Syllabus quiz | Jan 16, 11:59pm | Canvas | Canvas | 1% |
| hw1 | Jan 16, 11:59pm | Github repo | Gradescope | 3% |
| hw2 | Jan 23, 11:59pm | Github repo | Gradescope | 3% |
| hw3 | Feb 1, 11:59pm | Github repo | Gradescope | 4% |
| hw4 | Feb 10, 11:59pm | Github repo | Gradescope | 4% |
| Midterm | Feb 15 Wednesday | TBD | TBD | 19 % |
| hw5 | March 1, 11:59pm | Github repo | Gradescope | 4% |
| hw6 | Mar 15, 11:59pm | Github repo | Gradescope | 5% |
| hw7 | Mar 22, 11:59pm | Github repo | Gradescope | 4% |
| hw8 | April 12, 11:59pm | Github repo | Gradescope | 3% |
| Final exam | Apr 20, 7:00pm | TBD | TBD | 50% |
As per UBC Schedule, the final exam will be on Thursday, April 20th, from 7:00pm to 10pm (exam length TBD). No remote options allowed. Students will attend to the exam location based on the lecture section and last name.
Students who require special accommodations must register with CFA and take the exam at their facilities. Remember that CFA requires you to do so at least 1 week prior to UBC's final exam period. If you fail to register with CFA and can not take the exam with them, we will not be able to provide alternative accommodations and you will have to take the exam with the rest of the class.
If you believe that you will be experiencing an exam hardship, exam clash or any religious observations, please fill out this survey by Friday, March 31 @ 11:59 p.m. PT to request to take the final exam at an alternate time (TBD): https://ubc.ca1.qualtrics.com/jfe/form/SV_5yY8sjQatMZ0XlQ . More exam info to come.
Lectures will be on Tuesday and Thursday. Exact time and location change according to your section:
| Section | Day | Time | Location |
|---|---|---|---|
| 201 | Tue/Thu | 2:00 - 3:30 | Geography 100 |
| 202 | Tue/Thu | 3:30 - 5:00 | P. A. Woodward Instructional Resources Centre 3 |
| 203 | Tue/Thu | 5:00 - 6:30 | Hugh Dempster Pavilion 310 |
Lectures:
- Watch the "Pre-watch" videos before each lecture.
- You will find lecture notes from each instructor in this repository. Lectures will be posted as they become available.
| Date | Topic | Assigned videos and datasets | vs. CPSC 340 |
|---|---|---|---|
| Jan 10 | Course intro | 📹 |
n/a |
| Part I: ML fundamentals and preprocessing | |||
|
Week 1 datasets: |
|||
| Jan 12 | Decision trees | 📹 |
less depth |
| Jan 17 | ML fundamentals | 📹 |
similar |
|
Week 2 datasets: |
|||
| Jan 19 |
|
📹 |
less depth |
| Jan 24 | Preprocessing, sklearn pipelines |
📹 |
more depth |
|
Week 3 dataset: |
|||
| Jan 26 | More preprocessing, sklearn ColumnTransformer, text features |
📹 |
more depth |
|
Week 4 datasets: |
|||
| Jan 31 | Linear models | 📹 |
less depth |
|
Week 5 datasets: |
|||
| Feb 2 | Hyperparameter optimization, overfitting the validation set | 📹 |
different |
| Feb 7 | Evaluation metrics for classification | 📹 |
more depth |
|
Week 6 datasets: |
|||
| Feb 9 | Regression metrics | 📹 |
more depth on metrics less depth on regression |
| Feb 14 | Midterm review | ||
| Feb 15 | Midterm | On Wednesday! Note the different time! More details will be posted on Piazza | |
| Feb 16 | No lecture | ||
| Feb 19-25 | Reading week (no classes) | ||
|
Week 7 datasets: |
|||
| Feb 28 | Ensembles | 📹 |
similar |
| Mar 2 | Feature importances, model interpretation | 📹 |
feature importances is new, feature engineering is new |
| Mar 7 | Feature engineering and feature selection | None | less depth |
| Part II: Unsupervised learning, transfer learning, different learning settings | |||
| Mar 9 | Clustering | 📹 |
less depth |
| Mar 14 | More clustering | less depth | |
|
Week 9 datasets: |
|||
| Mar 16 | Simple recommender systems | None | less depth |
| Mar 21 | Text data, embeddings, topic modeling | 📹 |
new |
| Mar 23 | Neural networks and computer vision | less depth | |
| Mar 28 | Time series data | (Optional) Humour: The Problem with Time & Timezones | new |
| Mar 30 | Survival analysis | 📹 (Optional but highly recommended)Calling Bullshit 4.1: Right Censoring | new |
| Part III: Communication, ethics, deployment | |||
| April 4 | Ethics | 📹 (Optional but highly recommended) |
new |
| Apr 6 | Communication | 📹 (Optional but highly recommended) |
new |
| Apr 11 | Model deployment | new | |
| Apr 13 | Conclusions - TBD | new |