DIPARTIMENTO DI INGEGNERIA DELL'INFORMAZIONE
E SCIENZE MATEMATICHE

UNIVERSITA' DEGLI STUDI DI SIENA
 
Home
  Privacy e Cookie policy


Stefano Melacci


Dipartimento di Ingegneria dell'Informazione
e Scienze Matematiche
University of Siena
Via Roma, 56
53100 Siena ITALY


e-mail:
Tel: 0577233786
Fax: -
Office:
Building:
Floor:
Room:
S. Niccolò
1
111

[map]
Research Area Computer Science
Official Homepage https://docenti.unisi.it/it/melacci
Personal Homepage http://www.dii.unisi.it/~melacci
Office Hours
segreteriaonline
Curriculum
Stefano Melacci is a Senior Researcher (RTD B – Tenure-Track Assistant Professor) of the Department of Information Engineering and Mathematics, University of Siena (Siena, Italy), since January 2018. His profile is strongly characterized by research activity in the fields of Machine Learning and, more generally, Artificial Intelligence. In the last years, he has been Research Manager of the Italian company QuestIT S.r.l. (Siena, Italy), working on new technologies for Machine Learning-based Conversational Systems. Previously, he was a Research Fellow ("Assegnista di Ricerca") of the Department of Information Engineering and Mathematics, University of Siena, where he received his PhD (2010), and the M.S. Degree (cum Laude). Stefano Melacci studied and proposed Multi-Layer architectures (Deep Networks) for extracting information from static images and videos, using adaptive convolutional filters and principles from Information Theory (Developmental Visual Agents, "Learning to see like children", http://dva.diism.unisi.it). Several of the research contributes of Dr. Melacci are related to Kernel Machines and Regularization Theory (classification problems with supervised intervals, clustering and verification problems using minimal entropy criteria), under the unifying framework of Learning from Constraints (https://sites.google.com/site/semanticbasedregularization) that allows classic learning models to integrate symbolic knowledge representations. He has previously worked on Manifold Regularization algorithms and proposed Neural Networks for learning Similarly Measures, with applications to Computer Vision.



 

Username:
Password:


Dipartimento di Ingegneria dell'Informazione e Scienze Matematiche - Via Roma, 56 53100 SIENA - Italy