01 Foundations
How does a computer learn?
the path
01
How does a computer see data?
Text, images, sound: everything we give a computer has to become numbers first.
Vector representationWhat does a computer actually learn?
Some rules are too complex for anyone to write down.
Learn from examplesHow does it know it was wrong?
Computers learn from their mistakes, but only once we define what 'wrong' means.
LossHow does it improve?
Knowing you're wrong is half the problem. The other half is knowing what to change.
OptimizationDid it learn, or just memorize?
A perfect score can hide a serious problem.
GeneralizationHow do we keep it from memorizing?
Memorizing is the easiest way to a good score, but it's not the same as learning.
RegularizationHow sure is it?
Some answers are careful conclusions, and some are wild guesses.
Probability and uncertaintyHow do we measure if it works?
An AI can look impressive on paper and still fail at the job it was built for.
MetricsWhen does it stop working?
AI fails quietly, when the world where it learned from no longer exists.
Rare cases and Drift
Follow the path
Receive an email once a week with new waypoints.