1- Introduction to machine learning: Types, parameters, optimization (1.5 hrs) 2- Convolutional neural networks: Theory, parameters, and applications (2 hrs). 3- Deep learning in environmental engineering and geoscience (1.5 hrs). 4- Deep learning application – lab exercise (4 hrs). 5- Transfer learning for engineering application – lab exercise (3 hrs).

The course is intended for students who have basic or no background in machine learning-based data processing. Nevertheless, basic computer programming skills is required.

The course focuses on the use of machine learning algorithms in environmental engineering, with an emphasis on applications pertaining to geo-science and natural hazards. The course will help students to understand the potential, limitations, and implications of machine learning algorithms. It will also prepare them to apply these algorithms to actual engineering applications in the domain of natural hazards and geo-science data processing. The first part of the course covers the fundamentals of machine learning, the theory and parameters of convolutional neural networks and deep machine learning models, as well as an overview of machine learning implementation in environmental engineering and geoscience. The implementation and application of machine learning models to actual data sets is the main emphasis of the second half of the course.

In presenza

Prova di laboratorio di natura pratica sperimentale o informatico

P.D.1-1 - Dicembre