Intro to Machine Learning
An introductory practical machine learning course using Python with a strong application focus.
Time (timezone converted to UTC)
Sat, 9:20 – 10:00 PM UTC
Dates (mm/dd)
7/11, 7/18, 7/25, 8/1, 8/8, 8/15
Difficulty
Advanced
Ages (recommended)
10+
An introductory practical machine learning course with a strong application focus. Students will be expected to come into the course with a strong basic foundation in Python. We will use scikit-learn throughout the beginning half of the course and transition to PyTorch, a widely used open-source machine learning framework in the 2nd half.
Each class will contain a mix of lecture and hands-on lab time where students will code along with the instructor(s). The class will cover elements of both unsupervised and supervised learning.
Syllabus
| Week | Topic(s) |
|---|---|
| 1 | What is machine learning: supervised learning, regression vs classification problems |
| 2 | Linear & logistic regression, plotting & making graphs using matplotlib |
| 3 | Naive Bayesian classifiers, support vector machines (SVM), decision trees (theory) |
| 4 | Foundations of neural networks: perceptron model, gradient descent, ReLU, etc. |
| 5 | Implementing a basic neural network in PyTorch (plus some basic model validation and saving/loading weights) |
| 6 | Introduction to natural language processing using Transformers (Hugging Face) |