Math for AI
Syllabus
Linear algebra
Calculus + optimization methods
Probability theory + statistics
AI Academy
Linear
Algebra
AI Academy
01 Introduction to vectors, matrices
1 Vectors and linear 2 Lengths and dot products 3 Matrices, definition,
combinations matrix operations
AI Academy
02 Linear equations and Gaussian elimination
1 Vectors and linear equations 2 Gaussian elimination 3 Elimination using matrices
AI Academy
03 Matrix operations and decomposition
1 Rules for matrix 2 Inverse matrices, 3 LU decomposition;
operations conditions for existence, Transposes, symmetric,
Gauss-Jordan permutation matrices
elimination, Determinant
AI Academy
04 Vector spaces and subspaces
1 Vector spaces, 2 The nullspace of A: 3 The complete solution to
subspaces Solving Ax = 0 Ax = b
AI Academy
05 Independence, basis and dimension,
orthogonality
1 Linear independence, 2 Four fundamental 3 Orthogonal subspaces,
basis, dimension of vector subspaces (column, null, orthogonal complements
spaces row, left null) and their
dimensions
AI Academy
06 Orthogonality (cont’d)
1 Orthogonal bases, 2 Projection of vectors, 3 Least squares
Gramm-Schmidt process orthogonal projections approximation, fitting
linear models
AI Academy
07 Eigenvalues and eigenvectors
1 Eigenvalues, 2 Diagonalization, 3 Iterative estimates for
eigenvectors, conditions for eigenvalues /eigenvectors
characteristic equation diagonalization
AI Academy
08 Linear transformations
1 Definitions and properties 2 Representation of linear 3 SVD, computation and
of linear transformations transformations as applications
matrices
AI Academy
09 Final exam and projects
1 Review session 2 Comprehensive 3 Presenting final projects
assessment covering all that apply multiple linear
topics (final exam) algebra concepts
AI Academy
Calculus +
optimization
methods
AI Academy
01 Fundamentals of calculus for AI/ML
1 Introduction to Limits, 2 Continuity, types of 3 Limits at Infinity and
definition, limit laws discontinuities Infinite Limits
AI Academy
02 Differential calculus and its applications
1 Introduction to 2 Applications of 3 Second and higher-order
derivatives, definition, derivatives, tangent lines, derivatives, Taylor
rules of differentiation rates of change expansion
AI Academy
03 Integral calculus and its applications
1 Introduction to integrals, 2 Applications of integrals, 3 Techniques of integration
definition, fundamental areas, volumes (integration by parts,
theorem of calculus substitution)
AI Academy
04 Multivariable calculus for AI/ML
1 Partial Derivatives, chain 2 Gradient vectors, Hessian 3 Double integrals and
rule matrices, linear and applications
quadratic approximations
AI Academy
05 Optimization techniques in AI/ML (part1)
1 Gradient Descent 2 Gradient Descent with 3 BFGS
Variants - stochastic, Momentum, Adaptive
mini-batch Momentum (Adam);
Newton’s method
AI Academy
06 Optimization techniques in AI/ML (part2)
1 Conjugate gradient 2 Trust-region methods
AI Academy
07 Optimization techniques in AI/ML (part3)
1 Constrained optimization, Lagrange multipliers 2 KKT conditions
AI Academy
08 Advanced AI/ML applications
1 Case studies in AI/ML 2 Integrating techniques in 3 Review and preparation
AI/ML, combining for the final project
calculus and optimization
AI Academy
Probability
theory +
statistics
AI Academy
08
01 Introduction to probability theory
1 Fundamentals of 2 Conditional probability, 3 Random variables
probability independence, law of
total probability, chain Discrete random variables,
Basics of probability, event spaces probability mass function (PMF)
rule (product rule)
AI Academy
02 Intro (cont’d)
1 Random variables (cont’d) 2 Probability 3 Probability
distributions distributions (cont’d)
Continuous random variables,
probability density function (PDF) common distributions (Bernoulli, bivariate, marginal/conditional
beta, binomial, exponential, gamma, distributions, independent random
normal, Poisson) variables
AI Academy
03 Expectation, variance, and moments
1 Expectation and 2 Moments and moment 3 Covariance and
variance generating functions correlation
Definition and properties of Higher-order moments, moment Covariance, correlation, and their
expectation and variance generating functions properties
AI Academy
04 Bayesian probability
1 Bayes theorem 2 Bayesian inference 3 Bayesian networks
Bayes theorem, applications, and Bayesian inference, prior and Intro to bayesian networks
examples posterior distributions
AI Academy
05 Hypothesis testing and confidence
intervals
1 Hypothesis testing basic 2 Confidence intervals 3 Advanced hypothesis
testing
Null and alternative hypotheses, Constructing and interpreting
types of errors confidence intervals ANOVA, chi-square tests
AI Academy
06 Statistical inference and estimation
1 Point estimation 2 Interval estimation 3 Maximum likelihood
estimation (MLE)
Methods of point estimation, Constructing and interpreting
properties of estimators interval estimates Principles of MLE, applications
AI Academy
07 Markov chain and sampling methods
1 Markov chain 2 Standard distributions 3 Importance sampling,
MCMC, Gibbs sampling
Multinoulli, Gaussian
AI Academy
08 Review and final project
1 Review of the content 2 Final project
AI Academy
