Data e luogo
The beginning of the course is scheduled for November.
Motivazioni e obiettivi
Data mining (DM) or knowledge discovery in databases (KDD) and text mining (TM) have emerged as relevant fields of computer science. Their common goal is to discover previously unknown patterns from huge amount of data. DM applies to structured data while TM is devoted to process un-structured or semi-structured text. Some applicative domains of DM and TM are; business intelligence, finance, bioinformatics, medicine and transportation. The course will provide an overview of the main methods and algorithms used by DM and TM. Furthermore, the process flow of KDD will be presented to transform data into knowledge. The lectures will be structured with theoretical and practical sessions. Professional software will be presented and used to practically illustrate how data can be turned into knowledge. Different case studies will be presented and analyzed.
- Classification and estimation
- Association models
- Performance evaluation
- Topic models
- Information extraction
- Bayesian networks and classifiers
- Dynamic Bayesian networks
- Continuous time Bayesian networks
A dataset will be assigned, possibly associated with a scientific paper. The dataset must be analyzed and a paper must be prepared, not less than 5 pages no more than 8.
Slide powerpoint, note audio
Nessun approfondimento presente per questa pagina
|(C) Copyright 2016 - Dipartimento Informatica Sistemistica e Comunicazione
Viale Sarca, 336|
20126 Milano - Edificio U14
email@example.com - ultimo aggiornamento di questa pagina 18/09/2012