News


Convegno del gruppo nazionale per il calcolo scientifico dell'INDAM

posted Feb 19, 2018, 2:55 AM by Gabriella Casalino   [ updated Feb 19, 2018, 2:56 AM ]

Gabriella Casalino has presented her research project, awarded by INdAM GNCS prize "Progetto Giovani Ricercatori 2017", at "Convegno del gruppo nazionale per il calcolo scientifico dell'INDAM" that was held in Montecatini terme 14-16 February 2018.

SFLA2018 - June 25-29, 2018

posted Jan 10, 2018, 11:53 PM by Giovanna Castellano   [ updated Jan 11, 2018, 12:01 AM ]

The CILab is organizing the IV European Summer School on Fuzzy Logic and Applications which will be held in Bari from 25 to 29 June (sfla2018.di.uniba.it). The school is promoted by the European Society for Fuzzy Logic and Technology and aims at introducing the core aspects and the recent developments of Fuzzy Logic and related applications. The School proposes several courses delivered by world-leading experts in the field. A key aspect of the School is the focus on communication and collaboration among participants and lecturers, ensuring time for discussions so that a fruitful ground for exchanging knowledge can be established. PhD students and young researchers attending the school will be given also the opportunity to provide short presentations of their activities.

Tutorial on "Fuzzy Systems Software", Dr. José Alonso

posted Dec 1, 2017, 7:25 AM by Corrado Mencar   [ updated Dec 14, 2017, 2:34 AM by Giovanna Castellano ]

Special Session on Advances on Explainable Artificial Intelligence

posted Oct 27, 2017, 6:57 AM by Corrado Mencar

17th International Conference on Information Processing and Management of Uncertainty in Knowledge-based Systems (IPMU 2018)
11 - 15 June 2018, Cádiz, Spain


In the era of the Internet of Things and Big Data, data scientists are required to extract valuable knowledge from the given data. They first analyze, cure and pre-process data. Then, they apply Artificial Intelligence (AI) techniques to automatically extract knowledge from data. 
Our focus is on knowledge representation and how to enhance human-machine interaction. As remarked in the last challenge stated by the USA Defense Advanced Research Projects Agency (DARPA), 
even though current AI systems offer many benefits in many applications, their effectiveness is limited by a lack of explanation ability when interacting with humans. 
Accordingly, non-expert users, i.e., users without a strong background on AI, require a new generation of explainable AI systems. They are expected to naturally interact with humans, thus providing comprehensible explanations of decisions automatically made. The goal of this special session is to discuss and disseminate the most recent advancements focused on explainable artificial intelligence. The session goes a step ahead with respect to the previous events we organized (which were mainly focused on interpretable fuzzy systems) in some other conferences: joint IFSA-EUSFLAT 2009, ISDA 2009, WCCI 2010, WILF 2011, ESTYLF 2012, WCCI 2012, EUSFLAT 2013, IFSA-EUSFLAT2015, and FUZZ-IEEE2017.

Seminar on Data2Text Systems: “A hundred words are worth a million data”

posted Oct 12, 2017, 3:39 AM by Corrado Mencar   [ updated Dec 14, 2017, 2:34 AM by Giovanna Castellano ]

Prof. Dr. José María Alonso Moral
Centro Singular de Investigación en Tecnoloxías da Información (CiTIUS)
Universidade de Santiago de Compostela (USC), Spain

27 ottobre 2017, ore 9:30 – 11:30, Aula Hume, Dipartimento di Informatica

Data2Text Systems: 
“A hundred words are worth a million data”

Fuzzy Logic for Image Processing

posted Oct 2, 2017, 4:08 AM by Giovanna Castellano   [ updated Oct 2, 2017, 4:11 AM ]

Special Issue on Information (ISSN 2078-2489)   
An open access journal of information science and technology, data, knowledge, and communication.

ICANN2017 - Special Session on Learning from Data Streams

posted Sep 8, 2017, 3:19 AM by Giovanna Castellano   [ updated Sep 8, 2017, 9:53 AM ]

http://www.icann2017.org/index.php/conference-programme/special-sessions/

Organisers:
Giovanna Castellano (Dept. Computer Science, University of Bari, Italy)
Francesco Masulli (Dept. Computer and Information Sciences, University of Genova, Italy)

Nowadays a wide range of real-world scenarios yield data streams, i.e. collections of data being generated continuously either over time or over space. E-commerce and banking transactions, weather forecasting recordings and sensor data, customer reports and network traffic records are common examples of data streams produced every day.
Accordingly there is an urgent need of methods capable to handle and analyze streams of data that are usually vast in volume (or possibly infinite), high-dimensional and changing dynamically. Analysis of data streams requires learning algorithms that are specifically designed not only to handle very large data sets but also to adapt continuously and automatically to smooth evolutions (drifts) and abrupt changes (shifts) in the data distribution.
The main objective of this special session is to discuss the potential of learning techniques in challenging scenarios involving prediction and classification tasks in the realm of data streams.

Disponibilità per un progetto di tesi di laurea magistrale in High Performance Computing

posted Nov 13, 2015, 3:50 AM by Corrado Mencar

L'obiettivo del progetto è di sviluppare un modulo software prototipale per l'esecuzione di algoritmi genetici sull'infrastruttura HPC (High-Performance Computeing) “GALILEO” nell'ambito dell'iniziativa ISCRA (Italian SuperComputing Resource Allocation) del CINECA.

Il progetto mira a sviluppare una proof-of-concept che sarà utilizzata per valutare le sfide tecnologiche, nonché i rischi e i benefici dello sviluppo di algoritmi genetici per HPC.

In particolare, saranno affrontati i seguenti problemi: rappresentazione efficiente dei genotipi; applicazione efficiente degli operatori genetici (selezione, incrocio e mutazione); allocazione ottimale dei genotipi ai nodi computazionali disponibili.

Il modulo software sarà testato su un insieme di problemi di benchmark e valutato in termini di efficienza nell'uso delle risorse computazionali disponibili.


Per maggiori informazioni, contattare il dott. Corrado Mencar (corrado.mencar@uniba.it)


Link utili:

ISCRA (Italian SuperComputing Resource Allocation ): http://www.hpc.cineca.it/services/iscra

Supercomputer GALILEO: http://www.hpc.cineca.it/hardware/galileo

IFSA-EUSFLAT2015 - Special Session on Interpretable Fuzzy Systems

posted Dec 1, 2014, 2:33 AM by Corrado Mencar

http://www.softcomputing.es/metaspace/portal/12/475

1-10 of 11