Mathematics for Machine Learning

The module will cover and review fundamental mathematical concepts as tools of the trade, each motivated and illustrated by real ML and AI problems. Topics will include linear algebra (regression, the SVD, PCA), multivariate calculus (functional derivatives, the chain rule, matrix calculus), optimisation (conjugate gradients, Hessian, stochastic gradient descent, Lagrange multipliers), and basic statistical concepts (asymptotics and the law of large numbers).

Upon completion of the module the student will be able to:

  • formulate and interpret fundamental mathematical concepts from linear algebra, calculus and statistics required to study ML and AI at Master’s level;
  • summarise, explain, and critically review key assumptions and mathematical methods of peer-reviewed ML papers and textbooks;
  • apply various mathematical tools to model currently relevant ML and AI problems, in an elegant and effective manner.