Explain how ML systems learn patterns from data to make predictions on unseen inputs
Describe why large data and compute make ML practical and where it is used today
Outline the core mapping from features through training and inference to generalization
Distinguish supervised, unsupervised, reinforcement, and semi/self-supervised learning
Apply a simple end-to-end workflow from problem framing through monitoring and retraining
Match everyday tasks such as spam filtering, price estimation, and clustering to learning types
Identify beginner pitfalls including data leakage, bias, overfitting, and vague problem definitions
Who this course is for
Beginners starting a first machine learning course session; useful for learners new to ML who want core ideas, learning types, a basic workflow, and common pitfalls. No prior ML experience required; basic familiarity with data concepts is helpful.
