Sandro Morasca Course

Prof. Sandro Morasca from the Dipartimento di Scienze Teoriche e Applicate of Università degli Studi dell’Insubria visited us in June 2022 and taught a course on Feature Selection and Evaluation Metrics for Classifiers.

Abstract: Machine Learning is becoming a fundamental tool for acquiring information in all sorts of real-life applications. A Machine Learning classifier is learned via a number of phases, each of which needs to be carried out adequately, lest suboptimal classifiers are learned, which may lead to making suboptimal decisions.

The course will specifically address the following two activities.

• Feature Selection. Several techniques for selecting the most useful features will be introduced and discussed, along with their strengths and weaknesses.
• Evaluation Metrics. Several different performance metrics exist in the literature and are practically used. Depending on the specific performance metric chosen, a different classifier can be selected as optimal.

Short bio: Sandro Morasca is a Professor of Computer Science at the Dipartimento di Scienze Teoriche e Applicate of the Università degli Studi dell’Insubria in Como and Varese, Italy. He was an Associate and Assistant Professor at the Politecnico di Milano in Milano and Como, Italy, and a Faculty Research Assistant and later a Visiting Scientist at the Department of Computer Science of the University of Maryland at College Park. Sandro Morasca has been actively carrying out research in Empirical Software Engineering, Software Quality, Machine Learning, Software Verification, Open Source Software, Web Services, and Specification of Concurrent and Real-time Software Systems, and has published over 30 journal papers and over 90 conference papers. Sandro Morasca has been involved in several national and international projects and has served on the PC of a number of international Software Engineering conferences and on the editorial board of “Empirical Software Engineering: An International Journal,” published by Springer-Verlag.