By the end of this lecture
Four things you can do.
Explain learning as optimization
Write the empirical risk, take a gradient step by hand, and say what backpropagation caches and why.
Read architectures as priors
Locality, weight sharing, recurrence, attention: what each assumption saves and where it fails.
Diagnose generalization failures
Separate iid from shift and composition, and explain double descent without treating it as a law.
Judge confidence and uncertainty
Calibration, OOD, ensembles, adversarial examples — and what none of them guarantees.