Learning objectives
The course aims to provide a general knowledge of the main Machine Learning (ML) methodologies, with a particular focus on the biomedical field. Specifically, the course is designed to introduce the student to the basic rules of machine learning, as well as the knowledge of the necessary tools to manipulate data independently, extract useful information, and comprehend its significance.
Prerequisites
None. However, basic knowledge of statistics and linear algebra is recommended.
Course unit content
-Big Data and Artificial Intelligence
-Machine Learning (ML)
- ML applications in the biomedical field.
-Deep Learning (DL)
-DL applications in the biomedical field
Full programme
-Big Data: definitions; types of data
-Introduction to Artificial Intelligence
-Machine Learning: definitions and datasets; supervised, semi-supervised and unsupervised learning; classification, regression and clustering; overfitting/underfitting; ML algorithms.
- ML applications in the biomedical field and in radiology (radiomics)
-Deep learning: neural networks; DL tasks; DL algorithms.
- DL applications in the biomedical field
- Computer exercises with the open-source software “Orange Data Mining”.
Bibliography
Teaching material on the Elly platform.
Teaching methods
Classroom teaching and computer lab on the “Orange Data Mining” software.
Assessment methods and criteria
Written exam, mainly consisting in multiple-choice questions.
Other information
- - -
2030 agenda goals for sustainable development
- - -
