Objective: introducing concepts and techniques for collaborative development of large and complex software systems for industrial applications, including Java, software development lifecycle, best practices in software development as code testing, versioning, and design patterns.
Objective: Introduce the students to the machine learning fundamentals, to the main techniques on supervised learning, and to the principal application domains. Present evolutionary calculation. The course explains how to design, develop and evaluate simple ML-based end-to-end systems and, at the same time, how to describe their operations.
Objective: providing expertise for the management of clinical and biomedical data from computerized medical records, through the methods of health information technology and of process modeling.
Objective: introduce the student to the principles of learning from data based on statistics, and to the scientific treatment of data to obtain new and reproducible knowledge. Some of the main supervised and unsupervised statistical learning techniques are presented.
Objective: provide tools for the analysis of images and signals in the biomedical field.
Objective: presenting the most important conceptual aspects of information retrieval systems and both principles and techniques for data visualization.
Objective: introducing machine learning techniques for artificial vision and pattern recognition in sequential data.
Genome sequencing technologies have revolutionised our approach to study biological systems. From healthy tissues to diseases, many questions are approached through the collection of far larger sequencing datasets, and some argue that all modern biology is computational biology. Sequencing technologies can measure molecular states at various degrees of resolution and noise, and complex bioinformatics/ machine learning pipelines are required to extract complex patterns that characterise from basic cellular processes to disease progression.
Objective: providing advanced knowledge of both theoretical and practical programming in C / C ++ and Python, with particular regard to the principles of object oriented programming and best practices of software development (advanced use of version control systems, continuous integration, unit testing), and introducing the modern technology of algorithms development.
Objective: introducing cyber-physical systems, with particular regard to modeling them with hybrid formalisms and the formal verification of their properties. Presenting both notions and main techniques of Reinforcement Learning.
Objective: presenting statistical methods and computational analysis techniques in genomics.
Objective: introduce modern computational techniques and machine learning techniques for the analysis of natural language.
Objective: introducing the main algorithmic methods for the storage, compression and analysis of large amounts of biological data, with particular emphasis on the treatment of sequencing data produced with next generation sequencing technologies.
The course will introduce the student to the main problems, data sources, and models in Geophysics.
Objective: introducing to the main techniques for the design of algorithms and data structures to manipulate strings, trees and large graphs, in particular to compression techniques and randomization.
NOTE: The equivalent name of this course is "Algorithms for Massive Data".
The course will introduce the student to data sources, problems, main concepts and models in Earth Science, with a focus on analytics using these data.
Objective: introducing students to the fundamentals and practice of stochastic modeling, simulation of stochastic models and inference of parameters starting from observations, with a focus on scalability for large models.
The course will introduce the student to the main ideas, problems, models and data analytic methods in oceanography and in marine ecology.
Objective: introducing students to modern architectures for high performance computing. Students will learn how to properly test such architectures (computing power, bandwidth, latency, energy efficiency). Leveraging these skills, students will be introduced to the parallel programming based on MPI protocols (Message Passing Interface) and multi-threading with OpenMP.
Objective: providing expertise on optimization techniques, with applications to industrial design.
The course will introduce students to main ideas, problems, data sources and models in georesource identification and management and in energy production.
Objective: introducing students to the principles of data analysis, to data mining, and to machine learning (supervised and unsupervised learning).
Detailed description (a.a. 2017/18): See here.
Objective: You will learn how to organize, transform, analyse and visualize data, with a focus on the relational data model, and a detour to semistructured data. You will learn the fundamentals of data science using R environment.
The course introduces the main concepts in information theory and algorithmic information theory.
Objective: providing numerical analysis tools for scientific computing, with particular attention to linear algebra, polynomial approximation, numerical integration, numerical solution of ordinary differential equations and partial differential equations, approximation of eigenvalues and eigenvectors.
Objective: introducing techniques of analysis and statistical Bayesian inference.
The course aims at introducing the student to modeling and analysis techniques, also data-based, in the area of computational neusciences.
Objective: introducing students to computational management of data, in particular the characterization of an information system, data modeling, design and management of databases, including non-traditional ones (eg, unstructured documents, spatial data, biological data , multimedia data), to the fundamentals of distributed data and to methodologies and techniques for the management and analysis of big data.
Objective: presenting statistical analysis techniques for social networks and other social and economic networks.
NOTE: The equivalent name of this course is "Social Network Analysis".
Objective: presenting the basic elements and principles of inferential statistics and statistical techniques for the analysis of complex data.
Objective: introducing cyber-physical systems, with particular regard to modeling them with hybrid formalisms and the formal verification of their properties.
Objective: presenting advanced machine learning techniques, with a focus on deep learning and Bayesian methods.
Detailed description (a.a. 2017/18): See here.
Objective: providing students with the methodological, theoretical and practical tools to formulate linear programming models and combinatorial optimization problems and to solve them, even for high dimensionality problems, using appropriate optimization software.
Objective: introducing advanced computational and statistical techniques for the analysis of clinical data.
Objective: providing students with practical information on how to design data models and data structures, to manage metadata to optimize access and research, and to become familiar with interoperability standards. The course will focus on the concept of open data, with efficiency for big data projects, and the concept of cloud as an infrastructure for data management and their processes.
Objective: presenting advanced machine learning techniques, with a focus on Bayesian methods.