<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.4 20241031//EN"
        "https://jats.nlm.nih.gov/publishing/1.4/JATS-journalpublishing1-4.dtd">
<article         dtd-version="1.4">
            <front>

                <journal-meta>
                                                                <journal-id>tbv-bbmd</journal-id>
            <journal-title-group>
                                                                                    <journal-title>Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi</journal-title>
            </journal-title-group>
                            <issn pub-type="ppub">1305-8991</issn>
                                        <issn pub-type="epub">2618-5997</issn>
                                                                                            <publisher>
                    <publisher-name>Akademik Bilişim Vakfı</publisher-name>
                </publisher>
                    </journal-meta>
                <article-meta>
                                        <article-id/>
                                                                                                                                                                                            <title-group>
                                                                                                                        <trans-title-group xml:lang="en">
                                    <trans-title>Mini‐BatchingforArtificialNeuralNetworkTraining</trans-title>
                                </trans-title-group>
                                                                                                                                                                                                <article-title>Yapay Sinir Ağlarında Parçalı Eğitim</article-title>
                                                                                                    </title-group>
            
                                                    <contrib-group content-type="authors">
                                                                        <contrib contrib-type="author">
                                                                <name>
                                    <surname>Amasyalı</surname>
                                    <given-names>Mehmet Fatih</given-names>
                                </name>
                                                            </contrib>
                                                                                </contrib-group>
                        
                                        <pub-date pub-type="pub" iso-8601-date="20160624">
                    <day>06</day>
                    <month>24</month>
                    <year>2016</year>
                </pub-date>
                                        <volume>8</volume>
                                        <issue>1</issue>
                                        <fpage>25</fpage>
                                        <lpage>34</lpage>
                        
                        <history>
                                    <date date-type="received" iso-8601-date="20160624">
                        <day>06</day>
                        <month>24</month>
                        <year>2016</year>
                    </date>
                                            </history>
                                        <permissions>
                    <copyright-statement>Copyright © 2005, Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi</copyright-statement>
                    <copyright-year>2005</copyright-year>
                    <copyright-holder>Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi</copyright-holder>
                </permissions>
            
                                                                                                <trans-abstract xml:lang="en">
                            <p>When the large data sets are modeling with Artificial Neural Networks, the training set is divided into mini-batches to parallelize training phase.  In this way, training time is reduced. In this study, the effect of the mini-batch training was investigated when it applied to small data sets. In our experiments, 4 different learning algorithms over 11 datasets were used. It is shown that the mini-batch training is more successful than the full batch training with 3 learning algorithm.</p></trans-abstract>
                                                                                                                                    <abstract><p>Yapay sinir ağları ile büyük veri kümeleri modellenirken eğitimi paralelleştirmek için, eğitim kümesi ağa toptan yerine parçalara ayrılarak verilir. Bu sayede eğitim süresi azaltılır. Bu çalışmada parçalı eğitimin küçük veri kümelerine uygulandığındaki etkisi incelenmiştir. 4 farklı eğitim algoritması ve 11 veri kümesi üzerinde yapılan testlerde, 3 eğitim algoritması için parçalı eğitimin, toptan eğitimden daha başarılı olduğunu görülmüştür.</p></abstract>
                                                            
            
                                                                                        <kwd-group>
                                                    <kwd>Yapay Sinir Ağları</kwd>
                                                    <kwd>   Toptan Öğrenme</kwd>
                                                    <kwd>   Parçalı Öğrenme</kwd>
                                                    <kwd>   Tekil Öğrenme</kwd>
                                                    <kwd>   Makine Öğrenmesi</kwd>
                                                    <kwd>   Optimizasyon</kwd>
                                                    <kwd>   Yapay Zeka</kwd>
                                            </kwd-group>
                            
                                                <kwd-group xml:lang="en">
                                                    <kwd>Artificial Neural Network</kwd>
                                                    <kwd>   Batch Learning</kwd>
                                                    <kwd>   Mini-batch Learning</kwd>
                                                    <kwd>   Stochastic Learning</kwd>
                                                    <kwd>   Machine Learning</kwd>
                                                    <kwd>   Optimization</kwd>
                                                    <kwd>   Artificial Intelligence</kwd>
                                            </kwd-group>
                                                                                                                                        </article-meta>
    </front>
    <back>
                            <ref-list>
                                    <ref id="ref1">
                        <label>1</label>
                        <mixed-citation publication-type="journal">LeCun Y., Bottou, L., Orr, G. ve Muller, K., 1998. “Efficient BackProp”, in Orr, G. and Muller K. (Eds), Neural Networks: Tricks of the trade, Springer.</mixed-citation>
                    </ref>
                                    <ref id="ref2">
                        <label>2</label>
                        <mixed-citation publication-type="journal">Wilson, D.R., Martinez, T.R., 2003, &quot;The general inefficiency of batch training for gradient descent learning&quot;, Neural Networks, 16 (2003) 1429–1451, Elsevier.</mixed-citation>
                    </ref>
                                    <ref id="ref3">
                        <label>3</label>
                        <mixed-citation publication-type="journal">Dekel, O., Bachrach, R.G., Shamir, O., Xiao, L., 2012, &quot;Optimal Distributed Online Prediction Using Mini-Batches&quot;, Journal of Machine Learning Research, 13 (2012) 165- 202.</mixed-citation>
                    </ref>
                                    <ref id="ref4">
                        <label>4</label>
                        <mixed-citation publication-type="journal">Gimpel, K., Das, D., Smith, N.A., 2010, &quot;Distributed Asynchronous Online Learning for Natural Language Processing&quot;, CoNLL &#039;10 Proceedings of the Fourteenth Conference on Computational Natural Language Learning, 213-222.</mixed-citation>
                    </ref>
                                    <ref id="ref5">
                        <label>5</label>
                        <mixed-citation publication-type="journal">Zhao, K., Huang, L., 2013, &quot;Minibatch and Parallelization for Online Large Margin Structured Learning&quot;, Proceedings of NAACL- HLT 2013, 370–379.</mixed-citation>
                    </ref>
                                    <ref id="ref6">
                        <label>6</label>
                        <mixed-citation publication-type="journal">Cotter, A., Shamir, O., Srebro, N., ve Sridharan, K., 2011, &quot;Better Mini-Batch Algorithms via Accelerated Gradient Methods&quot;, Advances in Neural Information Processing Systems (NIPS).</mixed-citation>
                    </ref>
                                    <ref id="ref7">
                        <label>7</label>
                        <mixed-citation publication-type="journal">Mİller, M.F., 1993, &quot;A scaled conjugate gradient algorithm for fast supervised learning&quot;, NEURAL NETWORKS, 6(4), 525-533.</mixed-citation>
                    </ref>
                                    <ref id="ref8">
                        <label>8</label>
                        <mixed-citation publication-type="journal">Boyd, S., Vandenberghe, L., 2004, Convex Optimization, Cambridge University Press.</mixed-citation>
                    </ref>
                                    <ref id="ref9">
                        <label>9</label>
                        <mixed-citation publication-type="journal">Fletcher, R., 1987, Practical methods of optimization, New York: John Wiley &amp; Sons.</mixed-citation>
                    </ref>
                                    <ref id="ref10">
                        <label>10</label>
                        <mixed-citation publication-type="journal">Igel, C., Hüsken, M., 2003, &quot;Empirical evaluation of the improved Rprop learning algorithm&quot;, Neurocomputing, 50(C), 105-123.</mixed-citation>
                    </ref>
                                    <ref id="ref11">
                        <label>11</label>
                        <mixed-citation publication-type="journal">http://wangwzhao.googlepages.com/</mixed-citation>
                    </ref>
                                    <ref id="ref12">
                        <label>12</label>
                        <mixed-citation publication-type="journal">Blake, C.L., Merz, C.J., 1998, UCI Repository of www.ics.uci.edu/~mlearn/MLRepository.html Databases -</mixed-citation>
                    </ref>
                            </ref-list>
                    </back>
    </article>
