<?xml version="1.0" encoding="UTF-8"?>

<modsCollection xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.loc.gov/mods/v3" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-3.xsd">
<mods version="3.3">

<genre>conference paper</genre>

<titleInfo><title>Extrapolation and learning equations</title></titleInfo>


<note type="publicationStatus">published</note>


<note type="qualityControlled">yes</note>

<name type="personal">
  <namePart type="given">Georg S</namePart>
  <namePart type="family">Martius</namePart>
  <role><roleTerm type="text">author</roleTerm> </role><identifier type="local">3A276B68-F248-11E8-B48F-1D18A9856A87</identifier></name>
<name type="personal">
  <namePart type="given">Christoph</namePart>
  <namePart type="family">Lampert</namePart>
  <role><roleTerm type="text">author</roleTerm> </role><identifier type="local">40C20FD2-F248-11E8-B48F-1D18A9856A87</identifier><description xsi:type="identifierDefinition" type="orcid">0000-0001-8622-7887</description></name>







<name type="corporate">
  <namePart></namePart>
  <identifier type="local">ChLa</identifier>
  <role>
    <roleTerm type="text">department</roleTerm>
  </role>
</name>



<name type="conference">
  <namePart>ICLR: International Conference on Learning Representations</namePart>
</name>



<name type="corporate">
  <namePart>Lifelong Learning of Visual Scene Understanding</namePart>
  <role><roleTerm type="text">project</roleTerm></role>
</name>



<abstract lang="eng">In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs. In the natural sciences, however, finding an interpretable function for a phenomenon is the prime goal as it allows to understand and generalize results. This paper proposes a novel type of function learning network, called equation learner (EQL), that can learn analytical expressions and is able to extrapolate to unseen domains. It is implemented as an end-to-end differentiable feed-forward network and allows for efficient gradient based training. Due to sparsity regularization concise interpretable expressions can be obtained. Often the true underlying source expression is identified.</abstract>

<originInfo><publisher>International Conference on Learning Representations</publisher><dateIssued encoding="w3cdtf">2017</dateIssued><place><placeTerm type="text">Toulon, France</placeTerm></place>
</originInfo>
<language><languageTerm authority="iso639-2b" type="code">eng</languageTerm>
</language>



<relatedItem type="host"><titleInfo><title>5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings</title></titleInfo>
  <identifier type="arXiv">1610.02995</identifier>
<part>
</part>
</relatedItem>


<extension>
<bibliographicCitation>
<mla>Martius, Georg S., and Christoph Lampert. “Extrapolation and Learning Equations.” &lt;i&gt;5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings&lt;/i&gt;, International Conference on Learning Representations, 2017.</mla>
<ieee>G. S. Martius and C. Lampert, “Extrapolation and learning equations,” in &lt;i&gt;5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings&lt;/i&gt;, Toulon, France, 2017.</ieee>
<chicago>Martius, Georg S, and Christoph Lampert. “Extrapolation and Learning Equations.” In &lt;i&gt;5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings&lt;/i&gt;. International Conference on Learning Representations, 2017.</chicago>
<apa>Martius, G. S., &amp;#38; Lampert, C. (2017). Extrapolation and learning equations. In &lt;i&gt;5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings&lt;/i&gt;. Toulon, France: International Conference on Learning Representations.</apa>
<ama>Martius GS, Lampert C. Extrapolation and learning equations. In: &lt;i&gt;5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings&lt;/i&gt;. International Conference on Learning Representations; 2017.</ama>
<short>G.S. Martius, C. Lampert, in:, 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings, International Conference on Learning Representations, 2017.</short>
<ista>Martius GS, Lampert C. 2017. Extrapolation and learning equations. 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. ICLR: International Conference on Learning Representations.</ista>
</bibliographicCitation>
</extension>
<recordInfo><recordIdentifier>6841</recordIdentifier><recordCreationDate encoding="w3cdtf">2019-09-01T22:01:00Z</recordCreationDate><recordChangeDate encoding="w3cdtf">2021-01-12T08:09:17Z</recordChangeDate>
</recordInfo>
</mods>
</modsCollection>
