Math Foundations
The intuition behind every AI algorithm, through code, not textbooks.
22 lessons · 22 visual stories
0/22 complete · 0%
#LessonTypeLanguagesTimeOpen
01Linear Algebra IntuitionEvery AI model is just matrix math wearing a fancy hat.LearnPython, Julia45 min▸ Visual story02Vectors, Matrices & OperationsEvery neural network is just matrix multiplication with extra steps.BuildPython, Julia75 min▸ Visual story03Matrix TransformationsA matrix is a machine that reshapes space. Learn what it does to every point, and you understand the whole transformation.BuildPython, Julia75 min▸ Visual story04Calculus for Machine LearningDerivatives tell you which way is downhill. That is all a neural network needs to learn.Learn—45 min▸ Visual story05Chain Rule & Automatic DifferentiationThe chain rule is the engine behind every neural network that learns.Build—75 min▸ Visual story06Probability and DistributionsProbability is the language AI uses to express uncertainty.Learn—45 min▸ Visual story07Bayes' TheoremProbability is about what you expect. Bayes' theorem is about what you learn.Build—75 min▸ Visual story08OptimizationTraining a neural network is nothing more than finding the bottom of a valley.Build—75 min▸ Visual story09Information TheoryInformation theory measures surprise. Loss functions are built on it.Learn—45 min▸ Visual story10Dimensionality ReductionHigh-dimensional data has structure. You find it by looking from the right angle.Build—75 min▸ Visual story11Singular Value DecompositionSVD is the Swiss Army knife of linear algebra. Every matrix has one. Every data scientist needs one.BuildPython, Julia75 min▸ Visual story12Tensor OperationsTensors are the common language between data and deep learning. Every image, every sentence, every gradient flows through them.Build—75 min▸ Visual story13Numerical StabilityFloating point is a leaky abstraction. It will bite you during training, and you will not see it coming.Build—45 min▸ Visual story14Norms and DistancesYour distance function defines what "similar" means. Choose wrong and everything downstream breaks.Build—45 min▸ Visual story15Statistics for Machine LearningStatistics is how you know if your model actually works or just got lucky.Build—45 min▸ Visual story16Sampling MethodsSampling is how AI explores the space of possibilities.Build—75 min▸ Visual story17Linear SystemsSolving Ax = b is the oldest problem in mathematics that still runs your neural network.Build—75 min▸ Visual story18Convex OptimizationConvex problems have one valley. Neural networks have millions. Knowing the difference matters.Build—75 min▸ Visual story19Complex Numbers for AIThe square root of -1 is not imaginary. It is the key to rotations, frequencies, and half of signal processing.Learn—45 min▸ Visual story20The Fourier TransformEvery signal is a sum of sine waves. The Fourier transform tells you which ones.Build—75 min▸ Visual story21Graph Theory for Machine LearningGraphs are the data structure of relationships. If your data has connections, you need graph theory.Build—45 min▸ Visual story22Stochastic ProcessesRandomness with structure. The math behind random walks, Markov chains, and diffusion models.Learn—45 min▸ Visual story