# A MINSAT Approach for Learning in Logic Domains (Articolo in rivista)

- Type
- Prodotto della ricerca (Classe)
- Articolo in rivista (Classe)

- Label
- A MINSAT Approach for Learning in Logic Domains (Articolo in rivista) (literal)

- Anno
- 2002-01-01T00:00:00+01:00 (literal)

- Alternative label
- Felici, G.; Truemper, K. (2002)(literal)
**A MINSAT Approach for Learning in Logic Domains**

in INFORMS journal on computing

- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
- Felici, G.; Truemper, K. (literal)

- Pagina inizio
- 20 (literal)

- Pagina fine
- 36 (literal)

- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#altreInformazioni
- A software code that implements the method described in this paper has been produced and is now integrated in a comprehensive software system freely distributed and used by many researchers in the Data Mining community. (literal)

- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#numeroVolume
- 14 (literal)

- Rivista
- INFORMS journal on computing (Rivista)

- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#descrizioneSinteticaDelProdotto
- In this paper is described a method that efficiently performs the learning task in the logic domain. Such method has been used to extract from data logic formulas that can explain some particular characteristic of a dataset. Such problem is often referred to as supervised learning and is one of the main problems that is needed to solve for effective Data Mining. The method proposed is based on the exploitation of the logic properties of the data and in the formulation of a logic optimization problem whose solution produces a logic formula with the desidered properties. The optimization problem associated is a Minimum Cost Satisfiability Problem, known to be very difficult to solve. The main characteristics of this approach to Learning and Classification problems is to be found in the fact that it is able to find compact logic formulas to separate two sets of data and that such formulas can be understood and interpreted by human experts, and more importantly, automatically integrated into intelligent expert systems. Many different applications have been dealt with successufully using this approach. The research on which this method is based was conducted in collaboration with the University of Texas at Dallas, and has originated a number of further developments. (literal)

- Note
- ISI Web of Science (WOS) (literal)

- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
- Felici Giovanni, Istituto di Analisi dei sistemi ed Informatica \"Antonio Ruberti\" Consiglio Nazionale delle Ricerche, Viale Manzoni, 30 - 00185 Roma, Italy Truemper Klaus, University of Texas at Dallas, Computer Science Program, Box 830688 Richardson Texas 75083-0688 (USA) truemper@utdallas.edu (literal)

- Titolo
- A MINSAT Approach for Learning in Logic Domains (literal)

- Abstract
- This paper describes a method for learning logic relationships that correctly classify a given data set. The method derives from given logic data certain minimum cost satisfiability problems, solves these problems, and deduces from the solutions the desired logic relationships. Uses of the method include data mining, learning logic in expert systems, and identification of critical characteristics for recognition systems. Computational tests have proved that the method is fast and effective. (literal)

- Prodotto di
- Autore CNR
- GIOVANNI FELICI (UnitÃ di personale interno)

- Insieme di parole chiave
- Parole chiave di "A MINSAT Approach for Learning in Logic Domains" (Insieme di parole chiave)

#### Incoming links:

- Autore CNR di
- GIOVANNI FELICI (UnitÃ di personale interno)

- Prodotto
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#rivistaDi
- INFORMS journal on computing (Rivista)

- Insieme di parole chiave di
- Parole chiave di "A MINSAT Approach for Learning in Logic Domains" (Insieme di parole chiave)