Foundations of Machine Learning

This unit introduces core concepts, practical tools, and ethical considerations that form the foundation for machine learning. Students will explore data roles and sources, basic algorithms (perceptron, decision trees), tooling (Google account, Colab), hardware choices, and early career opportunities to prepare for deeper technical work in subsequent units.

Learning Objectives

• Analyze the roles, sources, and quality considerations of datasets and identify legal and ethical requirements (consent, permissions, and privacy) for their use
• Demonstrate the ability to create and configure a Google account, set up and run Python notebooks in Google Colab, and compare hardware options for model development
• Apply foundational machine learning techniques by implementing and testing simple models (perceptron, similarity measures, and decision trees), using basic feature combinations and data augmentation on example datasets
• Evaluate types of learning (supervised, unsupervised, reinforcement), interpret learning curves, and relate emerging applications (NLP, e-commerce, generative models) to potential career opportunities