Original Academy
Legacy mirror · noindex · upstream phase 1
Math Foundations
The intuition behind every AI algorithm, through code.
Provenance: this phase outline and its lesson readings are preserved from ai-engineering-from-scratch by Rohit Ghumare under the MIT License. InterviewsVector does not claim authorship. These archive pages remain available for old links and progress, but are excluded from indexing.
Attributed readings
- 01Linear Algebra IntuitionEvery AI model is just matrix math wearing a fancy hat.
- 02Vectors, Matrices & OperationsEvery neural network is just matrix multiplication with extra steps.
- 03Matrix Transformations & EigenvaluesA matrix is a machine that reshapes space. Learn what it does to every point, and you understand the whole transformation.
- 04Calculus for ML: Derivatives & GradientsDerivatives tell you which way is downhill. That is all a neural network needs to learn.
- 05Chain Rule & Automatic DifferentiationThe chain rule is the engine behind every neural network that learns.
- 06Probability & DistributionsProbability is the language AI uses to express uncertainty.
- 07Bayes' Theorem & Statistical ThinkingProbability is about what you expect. Bayes' theorem is about what you learn.
- 08Optimization: Gradient Descent FamilyTraining a neural network is nothing more than finding the bottom of a valley.
- 09Information Theory: Entropy, KL DivergenceInformation theory measures surprise. Loss functions are built on it.
- 10Dimensionality Reduction: PCA, t-SNE, UMAPHigh-dimensional data has structure. You find it by looking from the right angle.
- 11Singular Value DecompositionSVD is the Swiss Army knife of linear algebra. Every matrix has one. Every data scientist needs one.
- 12Tensor OperationsTensors are the common language between data and deep learning. Every image, every sentence, every gradient flows through them.
- 13Numerical StabilityFloating point is a leaky abstraction. It will bite you during training, and you will not see it coming.
- 14Norms & DistancesYour distance function defines what "similar" means. Choose wrong and everything downstream breaks.
- 15Statistics for MLStatistics is how you know if your model actually works or just got lucky.
- 16Sampling MethodsSampling is how AI explores the space of possibilities.
- 17Linear SystemsSolving Ax = b is the oldest problem in mathematics that still runs your neural network.
- 18Convex OptimizationConvex problems have one valley. Neural networks have millions. Knowing the difference matters.
- 19Complex Numbers for AIThe square root of -1 is not imaginary. It is the key to rotations, frequencies, and half of signal processing.
- 20The Fourier TransformEvery signal is a sum of sine waves. The Fourier transform tells you which ones.
- 21Graph Theory for MLGraphs are the data structure of relationships. If your data has connections, you need graph theory.
- 22Stochastic ProcessesRandomness with structure. The math behind random walks, Markov chains, and diffusion models.