Equipe BD
Equipe BD
Laboratoire d'InfoRmatique en Images et Systèmes d'information
UMR 5205 CNRS/INSA de Lyon/Université Claude Bernard Lyon 1/Université Lumière Lyon 2/Ecole Centrale de Lyon

You are here

On ubiquity of implications (and how to avoid computing all of them) (séminaire mensuel Liris)

Sergei O. Kuznetsov
Tuesday, March 12, 2013 - 10:30 to 12:00
INSA de Lyon, amphi Claude Chappe

Séminaire mensuel du LIRIS par Sergei O. Kuznetsov, National Research University Higher School of Economics (Moscow, Russia)


We discuss relationships of implications between attributes in object-attribute data tables to various important notions in computer science and artificial intelligence: functional dependencies, horn theories, emergent patterns, disjunctive version spaces, etc. The intractability of computing implication bases seems to be the main challenge for the use of implications in analyzing large data collections. Alternatives to generation of implication bases such as lazy-learning classification, target-driven generation of classifiers, and sampling are considered.