Questo sito utilizza cookie tecnici e di terze parti. Se vuoi saperne di più o negare il consenso consulta l'informativa sulla privacy. Proseguendo la navigazione o cliccando su "Chiudi" acconsenti all'uso dei cookie. Chiudi
vai al contenuto vai al menu principale vai alla sezione Accessibilità vai alla mappa del sito
Login | Italiano  English
Home page

June 08 Webinar: "Explainability, Intepretability and Sensitivity Analysis" with Prof. Emanuele Borgonovo - Bocconi University

The Webinar promoted by the Di.Gi.ES scientific laboratory Decisions_LAB coordinated by Prof. Massimiliano Ferrara will analyze some recent developments in the Machine Learning area. Guest of the meeting was Prof. Emanuele Borgonovo of Bocconi University, considered on the subject among the leading experts in the international arena.

To participate in the meeting, you will need to access the Microsoft TEAMS - Laboratorio Decisions_LAB platform

The code to join the laboratory is the following: eb092v6

Users not registered on the Microsoft TEAMS UNIRC platform, to take part in the meeting, must send an email to the address:


Prof. Emanuele Borgonovo

Short Bio
Ph.D. in Probabilistic Risk Assessment at the Massachusetts Institute of Technology, Cambridge, MA, USA. Thesis advisor: Prof George E. Apostolakis. He also completed his studies at Harvard University and the MIT Sloan School of Management. Graduated with full marks in Nuclear Engineering Mathematical-Physical Orientation, Polytechnic of Milan.

Full Professor in the Department of Decision Sciences and Director of the Bachelor in Economics, Management and Computer Science (BEMACS). He was director of the ELEUSI Research Center from 2008 to 2012.
He is President-Elect of the Decision Analysis Society (INFORMS), co-chair of the technical committee for the Uncertainty Analysis of the European Association for Safety and Effectiveness (ESRA) since 2013.
He is also co-Editor-In Chief of the European Jounal of Operational Research, scientific advisor of the Springer International Series in Operations Research and Management Science and member of the Scientific Committee of the Silvio Tronchetti Provera Foundation.

Webinar’s abstract

A growing research activity is developing for increasing interpretability of machine findings. When complex architectures are used, analysts are, in fact, exposed to the black-box effect. This seminar will review several methods used both in the machine learning and in the simulation community to make the black box more transparent. We shall discuss tools such as partial dependence functions, layerwise relevance propagation, as well as present several local and global sensitivity analysis methods, also proposing new tools and new findings on popular tools.

Via dell'Università, 25 (già Salita Melissari) - 89124 Reggio Calabria - CF 80006510806 - Fax 0965 332201 - URP:Indirizzo di posta elettronica dell'ufficio relazioni con il pubblico- PEC:Indirizzo di posta elettronica certificata dell'amministrazione
Feed RSS Facebook Twitter YouTube Instagram