Ciclo Annuale Unico

Goals

This course offers an introduction to the foundational mathematical aspects, widely used tools and scientific applications of modern machine learning (ML) and high-performance computing (HPC) methods.
Students will explore the core principles of supervised and unsupervised machine learning—including Gaussian process regression, neural networks, deep learning, and convolutional architectures—while simultaneously developing the skills to implement these models efficiently using parallel computing paradigms. Hands-on sessions will present these concepts in the context of real-world scientific applications.
By the end of the course, students will have a working knowledge on several topics of supervised and unsupervised ML and on the development of parallel and efficient algorithms for computational methods in natural sciences.

Required skills

Linear algebra. Calculus. Basic knowledge of statistics and statistical mechanics. Basic knowledge of a programming language among C, C++, Fortran, or Python.