Week 1: Intro + Setup
Summary
An introduction to the ML landscape: what machine learning is, the difference between supervised and unsupervised learning, and the types of problems ML can solve (regression, classification, clustering). The practical component covers Python fundamentals (variables, data types, control flow, functions) and PyTorch basics — tensor operations, matrix multiplication, broadcasting, reshaping, nn.Module, autograd, and building simple MLP pipelines for binary classification, multi-class classification, multi-label classification, and regression tasks.
Materials
What Is Machine Learning, Really?
A plain-English tour of ML paradigms — supervised vs. unsupervised learning, common problem types, and the end-to-end workflow from raw data to predictions.
Python Fundamentals for ML
Hands-on Python from zero: variables, data types, lists, tuples, dicts, sets, operators, control flow, I/O, and modules — with exercises you actually run.
Includes notebookPyTorch I — Tensors, Matmul & Broadcasting
Tensor creation, matrix multiplication with torch.matmul, element-wise ops, broadcasting rules, reshape/transpose, in-place operations, and mean aggregations.
Includes notebookPyTorch II — Building Complete Training Pipelines
Custom Dataset/DataLoader, a SimpleMLP with nn.Module, four loss functions (BCE, CrossEntropy, MSE, BCE with logits), Adam optimizer, and train/val/test loops.
Includes notebook