Missouri S&T Scholar's Mine Research RepositoryMissouri S&T Research
print 
Title: Abductive reasoning with recurrent neural networks
Author (s): Wunsch, Donald C.
Department/Lab Affiliations: Applied Computational Intelligence Laboratory
Electrical and Computer Engineering
Keywords: Abductive
Neural Networks
Reasoning
Issue Date: 2003-07
Publisher: Elsevier
Citation: Abdelbar M. Ashraf, Emad A.M. Andrews, and Donald C. Wunsch II, "Abductive Reasoning with Recurrent Neural Networks,” Neural Networks, July 2003.
Abstract: Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CBA) is a formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In previous work, we presented a method for using high order recurrent networks to find least cost proofs for CBA instances. Here, we present a method that significantly reduces the size of the neural network that is produced for a given CBA instance. We present experimental results describing the performance of this method and comparing its performance to that of the previous method.
Type: Article - Journal
text
In Title: Neural Networks
Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder
FULL COPYRIGHT INFORMATION:
http://www.elsevier.com/wps/find/authorsview.authors/authorsrights
Publisher URL:
http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6T08-48PD5B3-4&_user=1036314&_coverDate=07%2F31%2F2003&_rdoc=21&_fmt=full&_orig=browse&_srch=doc-info(%23toc%234856%232003%23999839994%23436434%23FLA%23display%23Volume)&_cdi=4856&_sort=d&_docanchor=&_ct=54&_acct=C000050731&_version=1&_urlVersion=0&_userid=1036314&md5=5dac92d04f481abab6c88831b044ea15
Link to this page:
http://scholarsmine.mst.edu/post_prints/AbductiveReasoningwithRecurrentNeuralNetworks_09007dcc804c0194.html



titleAbductive reasoning with recurrent neural networks
contributor.authorWunsch, Donald C.
contributor.deptlabApplied Computational Intelligence Laboratory
contributor.deptlabElectrical and Computer Engineering
subjectAbductive
subjectNeural Networks
subjectReasoning
date.issued2003-07
publisherElsevier
identifier.citationAbdelbar M. Ashraf, Emad A.M. Andrews, and Donald C. Wunsch II, "Abductive Reasoning with Recurrent Neural Networks,” Neural Networks, July 2003.
identifier.pub.URI
http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6T08-48PD5B3-4&_user=1036314&_coverDate=07%2F31%2F2003&_rdoc=21&_fmt=full&_orig=browse&_srch=doc-info(%23toc%234856%232003%23999839994%23436434%23FLA%23display%23Volume)&_cdi=4856&_sort=d&_docanchor=&_ct=54&_acct=C000050731&_version=1&_urlVersion=0&_userid=1036314&md5=5dac92d04f481abab6c88831b044ea15
description.abstractAbduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CBA) is a formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In previous work, we presented a method for using high order recurrent networks to find least cost proofs for CBA instances. Here, we present a method that significantly reduces the size of the neural network that is produced for a given CBA instance. We present experimental results describing the performance of this method and comparing its performance to that of the previous method.
typeArticle - Journal
type.DCMITypetext
type.statusPostprint
rightsThis material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder
rights.URI
http://www.elsevier.com/wps/find/authorsview.authors/authorsrights
relation.isPartOfNeural Networks
date.accessioned2007-04-11T17:00:48Z
date.available2008-03-24T20:29:22Z
identifier.persist.URI
http://scholarsmine.mst.edu/post_prints/AbductiveReasoningwithRecurrentNeuralNetworks_09007dcc804c0194.html