Mathematics for Artificial Intelligence II

The course consists of two modules that provide prerequisite knowledge in mathematics for technical application courses in machine learning and artificial intelligence. Module 1: Statistics and probability theory (7.5 credits) The module covers the foundations of probability and statistics theory. Key concepts include random experiments, outcomes and events, probability functions, conditional probability, random variables, standard distributions (e.g., Poisson distribution, exponential distribution, and normal distribution), measures of central tendency and dispersion, point and interval estimation, and hypothesis testing for normally distributed populations. Module 2: Optimisation (7.5 credits) The module covers linear and nonlinear optimisation, with and without constraints. Key concepts include Taylor series, necessary and sufficient conditions for optimality, convergence, Newton's method, derivative-free methods, and stochastic gradient descent methods.