We discuss a Probably Approximate Correct (PAC) learning paradigm for Boolean formulas, which we call PAC meditation, where the class of formulas to be learnt is not known in advance. We split the building of the hypothesis in various levels of increasing description complexity according to additional inductive biases received at run time. In order to give semantic value to the learnt formulas, the key operational aspect represented is the understandability of formulas, which requires their simplification at any level of description. We deepen this aspect in light of two alternative simplification methods, which we compare through a case study.

Learning rule representations from Boolean data / B. Apolloni, A. Brega, D. Malchiodi, G. Palmas, A.M. Zanaboni - In: Artificial neural networks and neural information processing-ICANN/ICONIP 2003 : joint international conference ICANN/ICINIP 2003, Istanbul, Turkey, June 26-29, 2003 : proceedings / [a cura di] O. Kaynak, E. Alpaydin, E. Oja, L. Xu. - Berlin : Springer, 2003. - ISBN 9783540404088. - pp. 875-882 (( Intervento presentato al 2003. convegno Joint 13th International Conference on Artificial Neural Networks and 10th International Conference on Neural Information Processing (ICANN/ICONIP) tenutosi a Istanbul.

Learning rule representations from Boolean data

B. Apolloni
Primo
;
A. Brega
Secondo
;
D. Malchiodi;A.M. Zanaboni
Ultimo
2003

Abstract

We discuss a Probably Approximate Correct (PAC) learning paradigm for Boolean formulas, which we call PAC meditation, where the class of formulas to be learnt is not known in advance. We split the building of the hypothesis in various levels of increasing description complexity according to additional inductive biases received at run time. In order to give semantic value to the learnt formulas, the key operational aspect represented is the understandability of formulas, which requires their simplification at any level of description. We deepen this aspect in light of two alternative simplification methods, which we compare through a case study.
Settore INF/01 - Informatica
European Neural Network Society
Asia-Pacific Neural Network Assembly
Book Part (author)
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2434/214270
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact