Get Started

Math Foundations

The intuition behind every AI algorithm, through code.

22 lessonsAbout 32 hoursExpert level11 free lessonsBy AI engineering expert Rohit Ghumare
Start this phase
0 of 22 done
  1. 01Linear Algebra IntuitionEvery AI model is just matrix math wearing a fancy hat.60 minutesLearnPython, JuliaFree lesson
  2. 02Vectors, Matrices & OperationsEvery neural network is just matrix multiplication with extra steps.60 minutesBuildPython, JuliaFree lesson
  3. 03Matrix TransformationsA matrix is a machine that reshapes space. Learn what it does to every point, and you understand the whole transformation.75 minutesBuildPython, JuliaFree lesson
  4. 04Calculus for Machine LearningDerivatives tell you which way is downhill. That is all a neural network needs to learn.60 minutesLearnPythonFree lesson
  5. 05Chain Rule & Automatic DifferentiationThe chain rule is the engine behind every neural network that learns.90 minutesBuildPythonFree lesson
  6. 06Probability and DistributionsProbability is the language AI uses to express uncertainty.75 minutesLearnPythonFree lesson
  7. 07Bayes' TheoremProbability is about what you expect. Bayes' theorem is about what you learn.75 minutesBuildPythonFree lesson
  8. 08OptimizationTraining a neural network is nothing more than finding the bottom of a valley.75 minutesBuildPythonFree lesson
  9. 09Information TheoryInformation theory measures surprise. Loss functions are built on it.60 minutesLearnPythonFree lesson
  10. 10Dimensionality ReductionHigh-dimensional data has structure. You find it by looking from the right angle.90 minutesBuildPythonFree lesson
  11. 11Singular Value DecompositionSVD is the Swiss Army knife of linear algebra. Every matrix has one. Every data scientist needs one.120 minutesBuildPython, JuliaFree lesson
  12. 12Tensor OperationsTensors are the common language between data and deep learning. Every image, every sentence, every gradient flows through them.90 minutesBuildPythonMembers
  13. 13Numerical StabilityFloating point is a leaky abstraction. It will bite you during training, and you will not see it coming.120 minutesBuildPythonMembers
  14. 14Norms and DistancesYour distance function defines what "similar" means. Choose wrong and everything downstream breaks.90 minutesBuildPythonMembers
  15. 15Statistics for Machine LearningStatistics is how you know if your model actually works or just got lucky.120 minutesBuildPythonMembers
  16. 16Sampling MethodsSampling is how AI explores the space of possibilities.120 minutesBuildPythonMembers
  17. 17Linear SystemsSolving $Ax = b$ is the oldest problem in mathematics that still runs your neural network.120 minutesBuildPythonMembers
  18. 18Convex OptimizationConvex problems have one valley. Neural networks have millions. Knowing the difference matters.90 minutesBuildPythonMembers
  19. 19Complex Numbers for AIThe square root of -1 is not imaginary. It is the key to rotations, frequencies, and half of signal processing.60 minutesLearnPythonMembers
  20. 20The Fourier TransformEvery signal is a sum of sine waves. The Fourier transform tells you which ones.90 minutesBuildPythonMembers
  21. 21Graph Theory for Machine LearningGraphs are the data structure of relationships. If your data has connections, you need graph theory.90 minutesBuildPythonMembers
  22. 22Stochastic ProcessesRandomness with structure. The math behind random walks, Markov chains, and diffusion models.75 minutesLearnPythonMembers
Next phase: ML Fundamentals →