User Tools

Site Tools


algorithm_corpus
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<?xml-stylesheet type="text/xsl" href="lexUnit.xsl"?>
<lexUnit xmlns="http://framenet.icsi.berkeley.edu" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" frame="Algorithm" frameID="652" status="Finished_Initial" POS="N" name="algorithm.n extend.v" ID="8538" totalAnnotated="26" xsi:schemaLocation="../schema/lexUnit.xsd">
    <header>
        <corpus description="BNC2" name="BNC2" ID="111">
            <document description="bncp" name="bncp" ID="421"/>
        </corpus>
        <frame>
            <FE fgColor="FFFFFF" bgColor="FF69B4" type="Core" abbrev="Algorithm" name="ML_Algorithm_type"/>
            <FE fgColor="FFFFFF" bgColor="004C99" type="Peripheral" abbrev="Instance" name="Instance"/>
            <FE fgColor="FFFFFF" bgColor="0000FF" type="Peripheral" abbrev="Task" name="ML_Task"/>
            <FE fgColor="FFFFFF" bgColor="99004C" type="Peripheral" abbrev="Data" name="Data"/>
            <FE fgColor="FFFFFF" bgColor="009900" type="Peripheral" abbrev="Hypothesis" name="Hypothesis"/>
            <FE fgColor="FFFFFF" bgColor="A0A0A0" type="Peripheral" abbrev="Software" name="Software"/>
            <FE fgColor="FFFFFF" bgColor="FF00FF" type="Peripheral" abbrev="Problem" name="Optimization_Problem"/>
        </frame>
    </header>
    <definition>This frame represents classes of ML algorithm types, their instances, tasks they address, data they specify, the type of hypothesis they produce, ML software (environment)  where they are implemented and
the optimization problem they try to solve.</definition>
    <lexeme POS="N" name="algorithm"/>
 
 
    <subCorpus name="01-unannotated-1">
        <sentence corpID="111" docID="421" sentNo="1" paragNo="181" aPos="0" ID="1215438">
            <text>We describe the IE-ID3 algorithm, which extends the Interval Estimation (IE) active learning approach from discrete to real-valued learning domains by combining IE with a classification tree learning algorithm (ID-3).</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1023/A:1018280807006"/>
                    <label cBy="351" end="31" start="23" name="Target"/>
                    <label cBy="351" end="46" start="40" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="100" start="77" name="ML_Algorithm_type"/>
                <label end="21" start="16" name="Instance"/>
                <label end="208" start="171" name="ML_Algorithm_type"/>
                <label end="214" start="211" name="Instance"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="2" paragNo="181" aPos="0" ID="1215438">
            <text>Most of these algorithms either extended or enhanced the well-known Perceptron algorithm(Agmon 1954; Rosenblatt 1958; Novikoff 1962), a pioneering online learning algorithm for linear prediction models.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-012-5319-2"/>
                    <label cBy="351" end="23" start="14" name="Target"/>
                    <label cBy="351" end="39" start="32" name="Target"/>
                    <label cBy="351" end="171" start="163" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="171" start="147" name="ML_Algorithm_type"/>
                <label end="77" start="68" name="Instance"/>
                <label end="200" start="177" name="Hypothesis"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
 
        <sentence corpID="111" docID="421" sentNo="3" paragNo="181" aPos="0" ID="1215438">
            <text>In this paper, we present, discuss, and analyze M-Qubed, a reinforcement learning algorithm designed to overcome these deficiencies by encoding and balancing best-response, cautious, and optimistic learning biases.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-010-5192-9"/>
                    <label cBy="351" end="90" start="73" name="Target"/>
                    <label cBy="351" end="205" start="198" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="90" start="59" name="ML_Algorithm_type"/>
                <label end="54" start="48" name="Instance"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="4" paragNo="181" aPos="0" ID="1215438">
            <text>It is very important to note that CoDL can naturally be presented as a general purpose semi-supervised learning algorithm for any CCM model.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-012-5296-5"/>
                    <label cBy="351" end="120" start="103" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="120" start="87" name="ML_Algorithm_type"/>
                <label end="37" start="34" name="Instance"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="6" paragNo="181" aPos="0" ID="1215438">
            <text>We show that this is a fundamentally relational learning problem and propose a new similarity measure for structured objects, which is built into a relational instance-based learning algorithm named DISTALL.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-006-8260-4"/>
                    <label cBy="351" end="197" start="193" name="Target"/>
                    <label cBy="351" end="191" start="174" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="191" start="148" name="ML_Algorithm_type"/>
                <label end="206" start="199" name="Instance"/>
                <label end="63" start="37" name="ML_Task"/>
                <label end="123" start="106" name="Data"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="7" paragNo="181" aPos="0" ID="1215438">
            <text>LSM is the state-of-the-art Markov logic network structure learning algorithm.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-015-5483-2"/>
                    <label cBy="351" end="77" start="59" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="77" start="28" name="ML_Algorithm_type"/>
                <label end="2" start="0" name="Instance"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="8" paragNo="181" aPos="0" ID="1215438">
            <text>In this paper, we describe a constructive decision tree learning algorithm, called XofN.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1023/A:1007626017208"/>
                    <label cBy="351" end="81" start="76" name="Target"/>
                    <label cBy="351" end="73" start="56" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="73" start="29" name="ML_Algorithm_type"/>
                <label end="86" start="83" name="Instance"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="9" paragNo="181" aPos="0" ID="1215438">
            <text>The learning algorithms are then often expressed as stochastic sampling techniques such as Gibbs sampling, Markov-chain Monte-Carlo, contrastive divergence</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5335-x"/>
                    <label cBy="351" end="22" start="0" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="70" start="51" name="ML_Algorithm_type"/>
                <label end="104" start="91" name="ML_Algorithm_type"/>
                <label end="131" start="107" name="ML_Algorithm_type"/>
                <label end="154" start="133" name="ML_Algorithm_type"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
 
        </sentence>
 
        <sentence corpID="111" docID="421" sentNo="10" paragNo="181" aPos="0" ID="1215438">
            <text>We note that other online, incremental reinforcement learning algorithms could be used in place of Sarsa(), for example policy gradient methods.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-012-5280-0"/>
                    <label cBy="351" end="71" start="53" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="71" start="19" name="ML_Algorithm_type"/>
                <label end="103" start="99" name="Instance"/>
                <label end="142" start="120" name="ML_Algorithm_type"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="11" paragNo="181" aPos="0" ID="1215438">
            <text>One of the simplest, and yet most consistently well-performing set of classifiers is the Nave Bayes models.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-006-6136-2"/>
                    <label cBy="351" end="104" start="100" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="80" start="70" name="ML_Algorithm_type"/>
                <label end="98" start="89" name="Instance"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
 
        </sentence>
        <sentence corpID="111" docID="421" sentNo="13" paragNo="181" aPos="0" ID="1215438">
            <text>Bagging and boosting are methods that generate a diverse ensemble of classifiers by manipulating the training data given to a base learning algorithm.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1023/A:1007607513941"/>
                    <label cBy="351" end="31" start="25" name="Target"/>
                    <label cBy="351" end="45" start="38" name="Target"/>
                    <label cBy="351" end="108" start="101" name="Target"/>
                    <label cBy="351" end="149" start="131" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="6" start="0" name="ML_Algorithm_type"/>
                    <label end="17" start="12" name="ML_Algorithm_type"/>
                    <label end="79" start="57" name="ML_Algorithm_type"/>
                    <label end="139" start="126" name="ML_Algorithm_type"/>
                    <label end="113" start="101" name="Data"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="14" paragNo="181" aPos="0" ID="1215438">
            <text>We also show that it is competitive with the metric learning algorithm LMNN (Weinberger and Saul 2009) and that plugging the learned distance into P-MinCq can further improve the results.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-014-5462-z"/>
                    <label cBy="351" end="69" start="52" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="69" start="45" name="ML_Algorithm_type"/>
                    <label end="74" start="71" name="Instance"/>
                    <label end="153" start="147" name="Instance"/>
                    <label end="140" start="125" name="Hypothesis"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
 
        <sentence corpID="111" docID="421" sentNo="15" paragNo="181" aPos="0" ID="1215438">
            <text>In Sect.2, we describe the sparse gradient learning algorithm for regression, where an automatic variable selection scheme is introduced.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-012-5284-9"/>
                    <label cBy="351" end="60" start="43" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="60" start="27" name="ML_Algorithm_type"/>
                    <label end="75" start="66" name="ML_Task"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
 
        <sentence corpID="111" docID="421" sentNo="16" paragNo="181" aPos="0" ID="1215438">
            <text>The learn-and-join algorithm is the state-of-the-art structure learning algorithm for Parametrized Bayes nets.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-006-5833-1"/>
                    <label cBy="351" end="27" start="19" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="108" start="53" name="ML_Algorithm_type"/>
                    <label end="17" start="4" name="Instance"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="17" paragNo="181" aPos="0" ID="1215438">
            <text>For the Alchemy-based structure-learning algorithms, we tried several different weight learning methods such as conjugate gradient and voted perceptron.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-015-5481-4"/>
                    <label cBy="351" end="50" start="32" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="50" start="22" name="ML_Algorithm_type"/>
                    <label end="14" start="8" name="Software"/>
                    <label end="102" start="80" name="ML_Algorithm_type"/>
                    <label end="129" start="112" name="ML_Algorithm_type"/>
                    <label end="151" start="135" name="ML_Algorithm_type"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="18" paragNo="181" aPos="0" ID="1215438">
            <text>The article describes a gradient search based reinforcement learning algorithm for two-player zero-sum games with imperfect information.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1023/A:1014063505958"/>
                    <label cBy="351" end="77" start="60" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="77" start="24" name="ML_Algorithm_type"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="19" paragNo="181" aPos="0" ID="1215438">
            <text>We have introduced a specialised meta-learning algorithm, based on the random forests framework (Breiman 2001), for predicting algorithm rankings, and provided both a theoretical and an empirical analysis.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5387-y"/>
                    <label cBy="351" end="56" start="47" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="56" start="33" name="ML_Algorithm_type"/>
                    <label end="94" start="71" name="ML_Algorithm_type"/>
                    <label end="144" start="116" name="ML_Task"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="20" paragNo="181" aPos="0" ID="1215438">
            <text>The Perceptron algorithm is perhaps the oldest online machine learning algorithm, tracing its origins back to the 1950s.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5327-x"/>
                    <label cBy="351" end="23" start="15" name="Target"/>
                    <label cBy="351" end="79" start="62" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="79" start="47" name="ML_Algorithm_type"/>
                    <label end="13" start="4" name="Instance"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="21" paragNo="181" aPos="0" ID="1215438">
            <text>This paper describes a learning algorithm, called BaLL, that enables mobile robots to learn what features/landmarks are best suited for localization, and also to train artificial neural networks for extracting them from the sensor data.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1023/A:1007554531242"/>
                    <label cBy="351" end="40" start="23" name="Target"/>
                    <label cBy="351" end="166" start="162" name="Target"/>
                    <label cBy="351" end="90" start="86" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="193" start="168" name="ML_Algorithm_type"/>
                    <label end="53" start="50" name="Instance"/>
                    <label end="234" start="224" name="Data"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="22" paragNo="181" aPos="0" ID="1215438">
            <text>We then apply our large-alphabet learning algorithms to the problem of approximate learning of analog circuits whose gate functions satisfy a Lipschitz condition.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/978-3-540-72927-3_6"/>
                    <label cBy="351" end="51" start="33" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="51" start="18" name="ML_Algorithm_type"/>
                    <label end="160" start="71" name="ML_Task"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="23" paragNo="181" aPos="0" ID="1215438">
            <text>In Sect.3.3, we present an online learning algorithm combining both binary learning and structured learning principles.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5407-y"/>
                    <label cBy="351" end="51" start="34" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="51" start="27" name="ML_Algorithm_type"/>
                    <label end="82" start="68" name="ML_Algorithm_type"/>
                    <label end="106" start="88" name="ML_Algorithm_type"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="24" paragNo="181" aPos="0" ID="1215438">
            <text>Our risk-sensitive reinforcement learning algorithm is based on a very different philosophy.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1023/A:1017940631555"/>
                    <label cBy="351" end="50" start="33" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="50" start="4" name="ML_Algorithm_type"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="25" paragNo="181" aPos="0" ID="1215438">
            <text>Our empirical study confirms that the proposed algorithms yield similar, if not better, prediction performance as the state-of-the-art online learning algorithms for DML but with significantly less amount of running time.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-014-5456-x"/>
                    <label cBy="351" end="56" start="47" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="168" start="135" name="ML_Algorithm_type"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="26" paragNo="181" aPos="0" ID="1215438">
            <text>The resulting learning algorithm,incremental version-space merging (IVSM), allows version spaces to contain arbitrary sets of classifiers, however generated, as long as they can be represented by boundary sets.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1023/A:1022600917598"/>
                    <label cBy="351" end="31" start="14" name="Target"/>
                    <label cBy="351" end="155" start="147" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="72" start="33" name="Instance"/>
                    <label end="136" start="118" name="ML_Algorithm_type"/>
                    <label end="208" start="196" name="Hypothesis"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
 
    </subCorpus>
</lexUnit>
algorithm_corpus.txt · Last modified: 2016/03/18 12:09 by pj