Student projects

The course integrates concepts from media studies, machine learning, multimedia and network science to characterize social practices and analyze content in sites like Facebook, Twitter and YouTube. Students will learn computational methods to infer individual and networked phenomena in social media.

The goal of this course is to provide the students with the main formalisms, models and algorithms required for the implementation of advanced speech processing applications (involving, among others, speech coding, speech analysis/synthesis, and speech recognition).

The Deep Learning for NLP course provides an overview of neural network based methods applied to text. The focus is on models particularly suited to the properties of human language, such as categorical, unbounded, and structured representations, and very large input and output vocabularies.

The goal of this course is to introduce the engineering students state-of-the-art speech and audio coding techniques with an emphasis on the integration of knowledge about sound production and auditory perception through signal processing techniques.

The module introduces students to practical AI agent development and AI-assisted software work in Python. It covers the construction of LLM-based agents, structured outputs, typed validation, tool calling, data analysis workflows, plotting, MCP-based tool integration, and vibecoding as a practical development methodology. Students work through hands-on exercises using real datasets and realistic programming tasks. They compare direct prompting, code-generating agents, safer tool-based workflows, and MCP-based architectures, while learning how to design, test, and evaluate AI-assisted systems. The course emphasizes practical implementation, critical assessment of agent behavior, and engineering trade-offs related to reliability, safety, maintainability, and human oversight.

Biometrics refers to the automated recognition of individuals based on their behavioural (speech, ...) and biological (face, fingerprint, iris, ...) characteristics for identification or authentication. It is a truly multidisciplinary domain at the intersection of bio-physiology, signal processing, machine learning, and cryptology, and provides multiple fundamental scientific challenges in these domains.This course is an introduction to analysis, modelling and interpretation of biometric data for biometric person recognition, forensic biometrics, cybersecurity and behavioural biometrics in man-machine communication.