Please use this identifier to cite or link to this item:
Author(s): Nuno Fonseca
Vítor Santos Costa
Fernando Silva
Rui Camacho
Title: Experimental evaluation of a caching technique
Issue Date: 2003
Abstract: Inductive Logic Programming (ILP) is a Machine Learning technique that hasbeen quite successful in knowledge discovery for relational domains. ILP systemsimplemented in Prolog challenge the limits of Prolog systems due to heavy usageof resources such as database accesses and memory usage, and to very longexecution times. The major reason to implement ILP systems in Prolog is thatthe inference mechanism implemented by the Prolog engine is fundamental tomost ILP learning algorithms. ILP systems can therefore benefit from the extensiveperformance improvement work that has taken place for Prolog. On theother hand, ILP is a non-classical Prolog application because it uses large setsof ground facts and requires storing a large search tree.One major criticism of ILP systems is that they often have long runningtimes. A technique that tries to tackle this problem is coverage caching [?]. Coveragecaching stores previous results in order to avoid recomputation. Naturally,this technique uses the Prolog internal database to store results. The questionis: does coverage caching successfully reduce the ILP systems running time?To obtain an answer to this question we evaluated the impact of the coveragecaching technique using the April [?] ILP system with the YAP Prolog system.To understand the results obtained we profiled Aprils execution and presentinitial results. The contribution of this paper is twofold: to an ILP researcher itprovides an evaluation of the coverage caching technique implemented in Prologusing well known datasets; to a Prolog implementation researcher it shows theneed of efficient internal database indexing mechanisms.
Subject: Engenharia de computadores, Engenharia electrotécnica, electrónica e informática
Computer engineering, Electrical engineering, Electronic engineering, Information engineering
Scientific areas: Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática
Engineering and technology::Electrical engineering, Electronic engineering, Information engineering
Source: 11th Portuguese Conference on Artificial Intelligence (EPIA 2003)
Document Type: Artigo em Livro de Atas de Conferência Internacional
Rights: openAccess
Appears in Collections:FEUP - Artigo em Livro de Atas de Conferência Internacional

Files in This Item:
File Description SizeFormat 
64563.pdfExperimental Evaluation of a Caching Technique122.24 kBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons