logo-polimi
Loading...
Manifesto
Cerca/Visualizza Manifesto
Dati Insegnamento
Stampe
Manifesto

Dettaglio Insegnamento

Contesto
Anno Accademico 2021/2022
Corso di Studi Dott. - MI (1383) Ingegneria Meccanica / Mechanical Engineering
Anno di Corso 1

Scheda Insegnamento
Codice Identificativo 057654
Denominazione Insegnamento STATISTICS IN THE BIG DATA ERA
Tipo Insegnamento MONODISCIPLINARE
Crediti Formativi Universitari (CFU) 5.0
Programma sintetico In the heart of industry 4.0 revolution is the aspect of big data. In this course we will view how big data affect the existing statistical methods, recognize the issues and propose tools that are capable to overcome the problems caused by the growth in the data size & dimension. We will start by recognizing the different types of big data (tall, wide, asynchronous, unstructured etc.) and we will present historic big data failures to acknowledge the challenges. We will present visualization principles, show platforms that facilitate visualization of complex data, talk about the concepts of statistical versus the practical significance and work on the issues of multiple hypothesis testing and correction. Statistical principles of data reduction (sufficiency and likelihood) will be provided. Within the supervised statistical learning, the descriptive versus predictive modeling approach will be discussed highlighting the differences between machine learning and statistics. Next we will focus into regression where we will talk about variable/model selection aspects along with shrinkage/regularization (like ridge, lasso etc.) and other penalizing methods. This material will be extended to generalized linear models and discriminant analysis as well. Within unsupervised statistical learning the topics of principal components analysis and cluster analysis will be covered. During the course big data from real studies will be used to present the material and students will be motivated to use data from their own research area to work on the various topics taught in class.
Settori Scientifico Disciplinari (SSD) --

Dettaglio
Scaglione Docente Programma dettagliato
Da (compreso) A (escluso)
A ZZZZ Tsiamyrtzis Panagiotis --
manifestidott v. 1.7.0 / 1.7.0
Area Servizi ICT
12/08/2022