Broadcasting, striding, and deleting the loop — the skill every framework is built on top of.
8h · 7 lessons · 1 challenge
Before this: Linear Algebra for Machine Learning, Python for ML Engineers
Broadcasting is the single most useful and most misunderstood rule in array programming. This module drills it until the rules are automatic, because the same rules govern PyTorch tensors, JAX arrays and every kernel you will later write.
The through-line is loop elimination: take working loop-based code and vectorize it, then measure. Most learners find their first hundredfold speedup here.
Two shapes appear. Broadcast, error, or a shape you must name — answer before the timer runs out. Streaks multiply your score.
Worth 300 XP.
