Course Schedule

Introduction to Machine Learning

14-Week Undergraduate Semester

Note: This schedule may be adjusted slightly based on class pace. All readings and labs use open educational resources.

Week 1—Introduction to Machine Learning & Open Tools

Topics

  • Artificial Intelligence vs. Machine Learning
  • The Machine Learning pipeline
  • Course overview and expectations
  • Introduction to Open Educational Resources (OER)

Lab

  • Python environment setup
  • Introduction to Jupyter notebooks

Week 2—Data Exploration & Linear Regression

Topics

  • Data representations and preprocessing
  • Linear regression models
  • Loss functions and intuition

Reading

  • Dive Into Deep Learning (D2L), Chapter 3

Lab 1

  • Data exploration using open datasets

Week 3—Logistic Regression & Classification

Topics

  • Binary classification
  • Logistic regression
  • Decision boundaries

Reading

  • Understanding Machine Learning, Chapter 9

Week 4—Optimization & Regularization

Topics

  • Gradient descent
  • Overfitting and underfitting
  • L1 and L2 regularization

Lab 2

  • Implementing linear and logistic regression

Week 5—Decision Trees & Ensemble Methods

Topics

  • Decision tree construction
  • Random forests
  • Bias–variance tradeoff

Lab 3

  • Classification using open datasets

Week 6—Support Vector Machines

Topics

  • Margin-based classifiers
  • Kernel intuition
  • Comparison with other classifiers

Week 7—Unsupervised Learning: Clustering & PCA

Topics

  • k-means clustering
  • Dimensionality reduction
  • Principal Component Analysis (PCA)

Lab 4

  • Clustering and pattern discovery

Week 8—Midterm Exam & Neural Network Fundamentals

Event

  • Midterm Exam (Weeks 1–7)

Topics

  • Perceptrons
  • Neural network architecture
  • Activation functions

Week 9—Deep Learning Introduction

Topics

  • Multi-layer neural networks
  • Backpropagation
  • Practical considerations

Reading

  • Dive Into Deep Learning (D2L), Chapters 4–5

Week 10—Model Evaluation & Validation

Topics

  • Train/test split
  • Cross-validation
  • Performance metrics

Lab 5

  • Model evaluation and comparison

Week 11—Feature Engineering & Model Improvement

Topics

  • Feature selection
  • Feature transformation
  • Improving model performance

Lab 6

  • Neural networks using PyTorch or TensorFlow

Week 12—Bias, Ethics, and Fairness in Machine Learning

Topics

  • Algorithmic bias
  • Ethical use of data
  • Responsible ML practices

Activity

  • Case study discussion using open datasets

Week 13—Final Project Development & Review

Topics

  • Project design and documentation
  • Reproducibility and open science

Activity

  • Finalizing reproducible notebooks
  • Peer feedback

Week 14—Final Project Presentations

Event

Course reflection and wrap-up

Student presentations of final projects