Show simple item record

dc.contributor.authorQaralleh, Esam
dc.contributor.authorAbandah, Gheith
dc.contributor.authorJamour, Fuad Tarek
dc.date.accessioned2015-04-28T11:58:42Z
dc.date.available2015-04-28T11:58:42Z
dc.date.issued2013-10-04
dc.identifier.citationTuning Recurrent Neural Networks for Recognizing Handwritten Arabic Words 2013, 06 (10):533 Journal of Software Engineering and Applications
dc.identifier.issn1945-3116
dc.identifier.issn1945-3124
dc.identifier.doi10.4236/jsea.2013.610064
dc.identifier.urihttp://hdl.handle.net/10754/550837
dc.description.abstractArtificial neural networks have the abilities to learn by example and are capable of solving problems that are hard to solve using ordinary rule-based programming. They have many design parameters that affect their performance such as the number and sizes of the hidden layers. Large sizes are slow and small sizes are generally not accurate. Tuning the neural network size is a hard task because the design space is often large and training is often a long process. We use design of experiments techniques to tune the recurrent neural network used in an Arabic handwriting recognition system. We show that best results are achieved with three hidden layers and two subsampling layers. To tune the sizes of these five layers, we use fractional factorial experiment design to limit the number of experiments to a feasible number. Moreover, we replicate the experiment configuration multiple times to overcome the randomness in the training process. The accuracy and time measurements are analyzed and modeled. The two models are then used to locate network sizes that are on the Pareto optimal frontier. The approach described in this paper reduces the label error from 26.2% to 19.8%.
dc.publisherScientific Research Publishing, Inc.
dc.relation.urlhttp://www.scirp.org/journal/PaperDownload.aspx?DOI=10.4236/jsea.2013.610064
dc.rightsThis is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
dc.subjectOptical Character Recognition
dc.subjectHandwritten Arabic Words
dc.subjectRecurrent Neural Networks
dc.subjectDesign of Experiments
dc.titleTuning Recurrent Neural Networks for Recognizing Handwritten Arabic Words
dc.typeArticle
dc.contributor.departmentComputer Science Program
dc.identifier.journalJournal of Software Engineering and Applications
dc.eprint.versionPublisher's Version/PDF
dc.contributor.institutionComputer Engineering Department, Princess Sumaya University for Technology, Amman, Jordan
dc.contributor.institutionComputer Engineering Department, The University of Jordan, Amman, Jordan
kaust.personJamour, Fuad Tarek
refterms.dateFOA2018-06-13T17:26:52Z
dc.date.published-online2013-10-04
dc.date.published-print2013


Files in this item

Thumbnail
Name:
JSEA_2013100411335625.pdf
Size:
718.9Kb
Format:
PDF
Description:
Main article

This item appears in the following Collection(s)

Show simple item record