Book 2 — Mathematics for AI/ML¶
Every concept here is built to connect directly to an ML mechanism.
Foundations¶
Linear Algebra¶
- Scalars, vectors, matrices, tensors
- Dot product & matrix multiplication
- Transpose, inverse, rank
- Linear independence, basis, span
- Eigenvalues & eigenvectors
- Orthogonality & projections
- Norms
- SVD
- PCA mathematics
Calculus¶
- Limits & derivatives
- Partial derivatives & chain rule
- Gradients, Jacobians, Hessians
- Multivariable calculus
- Optimization
Probability & Statistics¶
- Conditional probability & Bayes' theorem
- Random variables & distributions
- Expectation, variance, covariance
- Gaussian, Bernoulli, Binomial, Poisson
- Sampling & CLT
- Confidence intervals & hypothesis testing
- p-values & significance
- MLE / MAP / Bayesian inference
Status
Complete deep-dive coverage of mathematical foundations, linear algebra through SVD and PCA, calculus and optimization from limits to Adam, and probability and statistics through MLE, MAP and Bayesian inference.