(Enter summary)
Abstract: . RTL is an algorithm designed to learn any number of simple, mutually
dependent relations, producing recursive programs that are stratified in the sense given
by Apt. In this paper, we present a revised algorithm and its implementation based on
previous theoretical works that establish properties and limits of the learning framework.
The algorithm is described both in abstract form and through an example. Emphasis is
put on the way RTL uses induction and domain knowledge to guide the... (Update)
Context of citations to this paper: More
.... learning systems can easily be extended in order to learn recursive concepts, as in the system RTL (Giordana et al. 1993a; Baroglio and Botta, 1995); on the other hand, such an extension may not be so easy for other systems, as shown in (Cameron Jones and Quinlan, 1993)...
.... and Limitations There are some ILP systems that are able to learn multi class concepts represented in first order rules, such as RTL [1], ICL[7] MULT ICN[9] Nevertheless, it is still possible that some unseen data may not exactly match the rules produced by these systems....
Cited by: More
Approximate ILP Rules by Backpropagation Neural Network.. - Kijsirikul, Sinthupinyo (1999)
(Correct)
Integrating Multiple Learning Strategies in First Order Logics - Giordana, Neri, al. (1997)
(Correct)
Active bibliography (related documents): More All
0.5: Learning First Order Theories - Botta (1994)
(Correct)
0.3: Inductive Logic Programming: Theory And Methods - Muggleton, De Raedt (1994)
(Correct)
0.3: Architecture for Iterative Learning of Recursive Definitions - Jorge, Brazdil (1996)
(Correct)
Similar documents based on text: More All
0.4: Relational Learning as Search in a Critical Region - Botta, Giordana, Saitta.. (2003)
(Correct)
0.3: Discovering Complex Events in Long Sequences - Marco Botta Botta
(Correct)
0.3: Learning in the 'Real World' - Saitta, Neri (1998)
(Correct)
BibTeX entry: (Update)
Baroglio, C. and Botta, M. (1995). Multiple predicate learning with RTL. In 4th Congress of the Italian Association for Artificial Intelligence AI*IA'95, pages 44--55, Florence, Italy. http://citeseer.ist.psu.edu/baroglio95multiple.html More
@inproceedings{ botta95multiple,
author = "C. Baroglio \and M. Botta",
title = "Multiple Predicate Learning with {RTL}",
booktitle = "Topics in Artificial Intelligence",
volume = "LNAI 992",
publisher = "Springer",
editor = "M. Gori and G. Soda",
year = "1995",
url = "citeseer.ist.psu.edu/baroglio95multiple.html" }
Citations (may not include all citations):
435
Towards a Theory of Declarative Knowledge (context) - Apt, Blair et al. - 1988
3
Learning Mutually Dependent Relations (context) - Baroglio, Giordana et al. - 1992
2
Learning First Order Theories
- Botta - 1994
2
SMART+: A Multi-Strategy Learning Tool (context) - Botta, Giordana - 1993
Documents on the same site (http://www.di.unito.it/~mluser/SELECTbib.html):
FONN: Combining First Order Logic with Connectionist Learning - Botta, Giordana, Piola (1997)
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC