Current Courses
Computing Workshop is not currrently offering any courses.
Past Courses
Fundamentals of Machine Learning with Python (CDSI) - Summer 2023
This course is taught in an intensive one-week summer school format with 4 hours of instruction per day, split into a morning and an afternoon session. This instalment of Computing Workshop is presented in collaboration with McGill’s CDSI.
Lesson 0: Welcome! ML pipeline overview, appropriateness of ML, Python refresher (slides)
Lesson 1: Data acquisition and k-nearest neighbours (slides) (KNN worksheet) (KNN Jupyter Notebook)
Lesson 2: Data cleaning and decision trees (slides) (sample dataset, courtesy of Obviously AI) (data exploration notebook) (decision tree notebook)
Lesson 3: Unsupervised learning and model validation (slides) (clustering worksheet) (lab resources) (DBSCAN notebook)
Lesson 4: Neural networks and model training, reflecting on AI (slides) (Neural networks notebook)
Fundamentals of Machine Learning with Python (CDSI) - Winter 2023
This course is taught in a weekly format with 2 hours of instruction per session, in collaboration with McGill’s CDSI.
Lesson 0: Welcome! ML pipeline overview, appropriateness of ML, k-nearest neighbours (slides) (KNN worksheet) (KNN Jupyter Notebook)
Lesson 1: Data cleaning, regression, and decision trees (slides) (sample dataset, courtesy of Obviously AI) (data exploration notebook) (decision tree notebook)
Lesson 2: Unsupervised learning and model validation (slides) (clustering worksheet) (lab resources) (DBSCAN notebook)
Lesson 3: Neural networks and model training (slides) (Neural networks notebook)
Intro Python (CDSI) - Summer 2022
This course was taught in an intensive one-week format with 4 hours of instruction per day, in collaboration with McGill’s CDSI.
Machine Learning (B21) - Winter 2019
This course was taught in a weekly format with 2 hours of instruction per session, in collaboration with McGill’s Building21.
Lesson 0: Welcome! (Types and values worksheet) (slides)
Lesson 1: K nearest neighbours (slides) (Types and values recap) (Data structures recap) (KNN worksheet) (KNN interactive web site) (KNN Jupyter Notebook)
Lesson 2: Decision trees (slides) (Decision trees notebook) (Decision tree visualization)
Lesson 3: Neural networks (slides) (Neural network notebook) (Neural network POGIL)
Lesson 4: Neural networks, and coding lab (slides) (lab resources)
Lesson 5: Unsupervised learning and ML ethics (slides) (lab resources) (K-means POGIL)
Software (B21) - Fall 2018
This course was taught in a weekly format with 2 hours of instruction per session, in collaboration with McGill’s Building21.
Lesson 0: Welcome! (slides)
Lesson 1: K nearest neighbours (slides)
Lesson 2: Decision trees (slides)
Lesson 3: Neural networks. (slides)
Lesson 4: Applications of machine learning and coding lab (slides)
Lesson 5: Unsupervised learning and ethical problems of machine learning. (slides)
Hardware (B21) - Fall 2018
This course was taught in a weekly format with 2 hours of instruction per session, in collaboration with McGill’s Building21.
Lesson 0: Welcome! (slides)
Lesson 1: Binary and logic (slides)
Lesson 2: Integrated circuits, and the ALU (slides)
Lesson 3: Memory and storage (slides)
Lesson 4: Processor and machine code (slides)
Lesson 5: Operating systems (slides)
Computing Workshop (B21) - Fall 2017
This course was taught in a weekly format with 2 hours of instruction per session, in collaboration with McGill’s Building21.
Lesson 8: Remedial web development work (no slides or lesson plan)