AI/ML Mathematics Roadmap — 4-Year Mastery Blueprint

A free, interactive, semester-wise mathematics roadmap for B.Tech AI/ML students. Learn the math behind artificial intelligence and machine learning — from Class 12 foundations to research-grade theory. Built by Debojyoti Pal.

Why Mathematics for AI and Machine Learning?

Every machine learning algorithm is built on mathematics. Linear algebra powers neural networks and data transformations. Calculus enables gradient descent and backpropagation. Probability theory underpins Bayesian inference and generative models. Optimization theory explains how models are trained. This roadmap gives you a structured, semester-wise path through all of it.

Year 1 — Mathematical Foundations

Semester 1

Pre-Calculus and Algebra Refresh

Sets, relations, functions, polynomials, exponentials, logarithms, trigonometry, sequences and series, complex numbers. Fills Class 12 gaps before rigorous calculus.

Single-Variable Calculus

Limits and continuity, differentiation rules, chain rule, Mean Value Theorem, integration, Riemann sums, Fundamental Theorem of Calculus, Taylor and Maclaurin series. Essential for gradient descent and loss functions.

Logic and Proof Writing

Propositional logic, predicate logic, proof by induction, contradiction, sets and functions, countability. Foundation of formal mathematical reasoning.

Semester 2

Linear Algebra I

Vectors, dot product, cross product, matrices, transpose, inverse, Gaussian elimination, vector spaces, subspaces, span, basis, linear transformations, determinants. Everything in ML is linear algebra.

Discrete Mathematics

Combinatorics, permutations, combinations, graph theory, recurrence relations, Boolean algebra. Foundation for algorithm analysis and probabilistic models.

Year 2 — Core Mathematics for Machine Learning

Semester 3

Linear Algebra II

Eigenvalues and eigenvectors, diagonalization, Singular Value Decomposition (SVD), Principal Component Analysis (PCA) from SVD, positive definite matrices, L1 L2 Frobenius norms, Jacobian matrix, Hessian matrix, matrix calculus. SVD powers recommender systems and compression. Hessian used in second-order optimizers.

Probability Theory I

Sample space, events, Bayes theorem, random variables, PMF, PDF, CDF, expectation, variance, moments, Bernoulli, Binomial, Poisson, Normal, Exponential distributions. Every ML model makes probabilistic assumptions.

Semester 4

Multivariable Calculus

Partial derivatives, gradient vector, directional derivatives, chain rule for multiple variables, Jacobian, Hessian, Lagrange multipliers, constrained optimization. Backpropagation is multivariable chain rule applied recursively.

Probability Theory II

Joint distributions, marginal distributions, covariance, correlation, Multivariate Normal distribution, Central Limit Theorem, Law of Large Numbers, Markov chains. Required for Bayesian models, GANs, and VAEs.

Year 3 — Applied and Advanced Mathematics

Semester 5

Mathematical Optimization

Convex sets, convex functions, convex optimization, gradient descent derivation, stochastic gradient descent, mini-batch SGD, momentum, Adam optimizer mathematics, KKT conditions, duality theory. Training any neural network is solving an optimization problem.

Statistics and Estimation

Maximum Likelihood Estimation (MLE), Maximum A Posteriori (MAP), bias-variance tradeoff, confidence intervals, hypothesis testing, Bayesian inference, conjugate priors, Ordinary Least Squares (OLS), Ridge regression, Lasso regression. MLE and MAP are the theoretical basis of model training.

Semester 6

Information Theory

Entropy, joint entropy, conditional entropy, KL Divergence, cross-entropy loss, mutual information, Fisher information. Cross-entropy loss, VAE ELBO, and attention mechanisms all come from information theory.

Numerical Methods

Floating point arithmetic, numerical stability, Newton-Raphson root finding, numerical integration, LU decomposition, QR decomposition, conjugate gradient, condition numbers. GPU computation and stable training depend on numerical methods.

Stochastic Processes

Markov chains, stationary distributions, Hidden Markov Models, Gaussian processes, Brownian motion, MCMC, Metropolis-Hastings, Gibbs sampling. Used in reinforcement learning and diffusion models.

Year 4 — Research-Grade Mathematics

Semester 7

Functional Analysis and Measure Theory

Metric spaces, normed spaces, Hilbert spaces, inner product spaces, Reproducing Kernel Hilbert Spaces (RKHS), sigma-algebras, Lebesgue integral, convergence types. Required for kernel methods, SVMs, and PAC learning theory.

Probabilistic Graphical Models

Directed and undirected graphical models, belief propagation, variational inference, ELBO derivation, Expectation-Maximization (EM) algorithm, Variational Autoencoders (VAE) mathematics. Backbone of generative models.

Semester 8

Differential Geometry for Machine Learning

Manifolds, tangent spaces, Riemannian geometry, geodesics, Lie groups, Lie algebras, latent space geometry, natural gradient. Used in geometric deep learning and graph neural networks.

Statistical Learning Theory

PAC learning, VC dimension, Rademacher complexity, generalization bounds, minimax risk, online learning regret bounds. Rigorously answers why machine learning generalizes.

Advanced Optimization

Natural gradient descent, Newton method, L-BFGS, optimal transport, Wasserstein distance, mirror descent, non-convex optimization landscape. Powers state-of-the-art model training.

Recommended Resources for AI/ML Mathematics

  • 3Blue1Brown — Essence of Linear Algebra (YouTube)
  • 3Blue1Brown — Essence of Calculus (YouTube)
  • StatQuest with Josh Starmer — Statistics Fundamentals (YouTube)
  • MIT 18.06 Gilbert Strang — Linear Algebra Lectures (YouTube)
  • Mathematics for Machine Learning — Deisenroth (Book)
  • Convex Optimization — Boyd and Vandenberghe (Book)
  • Introduction to Probability — Blitzstein and Hwang (Book)

Built by Debojyoti Pal — indie developer and AI/ML builder. GitHub: github.com/Debojyoti-hub-tech. Instagram: @_coral_soul_