<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE ep-patent-document PUBLIC "-//EPO//EP PATENT DOCUMENT 1.7//EN" "ep-patent-document-v1-7.dtd">
<!-- This XML data has been generated under the supervision of the European Patent Office -->
<ep-patent-document id="EP16809572B8W1" file="EP16809572W1B8.xml" lang="en" country="EP" doc-number="3360087" kind="B8" correction-code="W1" date-publ="20240717" status="c" dtd-version="ep-patent-document-v1-7">
<SDOBI lang="en"><B000><eptags><B001EP>ATBECHDEDKESFRGBGRITLILUNLSEMCPTIESILTLVFIROMKCYALTRBGCZEEHUPLSK..HRIS..MTNORS..SM..................</B001EP><B003EP>*</B003EP><B005EP>J</B005EP><B007EP>0009290-CORR01</B007EP></eptags></B000><B100><B110>3360087</B110><B120><B121>CORRECTED EUROPEAN PATENT SPECIFICATION</B121></B120><B130>B8</B130><B132EP>B1</B132EP><B140><date>20240717</date></B140><B150><B151>W1</B151><B153>73</B153><B155><B1551>de</B1551><B1552>Bibliographie</B1552><B1551>en</B1551><B1552>Bibliography</B1552><B1551>fr</B1551><B1552>Bibliographie</B1552></B155></B150><B190>EP</B190></B100><B200><B210>16809572.7</B210><B220><date>20161111</date></B220><B240><B241><date>20180510</date></B241><B242><date>20210721</date></B242></B240><B250>en</B250><B251EP>en</B251EP><B260>en</B260></B200><B300><B310>201562254618 P</B310><B320><date>20151112</date></B320><B330><ctry>US</ctry></B330></B300><B400><B405><date>20240717</date><bnum>202429</bnum></B405><B430><date>20180815</date><bnum>201833</bnum></B430><B450><date>20240410</date><bnum>202415</bnum></B450><B452EP><date>20231027</date></B452EP><B480><date>20240717</date><bnum>202429</bnum></B480></B400><B500><B510EP><classification-ipcr sequence="1"><text>G06N   3/084       20230101AFI20231007BHEP        </text></classification-ipcr><classification-ipcr sequence="2"><text>G06N   3/09        20230101ALI20231007BHEP        </text></classification-ipcr><classification-ipcr sequence="3"><text>G06N   3/045       20230101ALI20231007BHEP        </text></classification-ipcr></B510EP><B520EP><classifications-cpc><classification-cpc sequence="1"><text>G06N   3/084       20130101 FI20210713BHEP        </text></classification-cpc><classification-cpc sequence="2"><text>G06N   3/045       20230101 LI20230101BHEP        </text></classification-cpc><classification-cpc sequence="3"><text>G06N   3/09        20230101 LI20231006BHEP        </text></classification-cpc></classifications-cpc></B520EP><B540><B541>de</B541><B542>TRAINIEREN VON NEURONALEN NETZEN MITTELS NORMALISIERTER ZIELAUSGÄNGE</B542><B541>en</B541><B542>TRAINING NEURAL NETWORKS USING NORMALIZED TARGET OUTPUTS</B542><B541>fr</B541><B542>APPRENTISSAGE DE RÉSEAUX NEURONAUX À L'AIDE DE SORTIES CIBLES NORMALISÉES</B542></B540><B560><B561><text>EP-A2- 1 215 627</text></B561><B562><text>M. TYGERT ET AL: "Scale-invariant learning and convolutional networks", ARXIV:1506.08230V2, 13 September 2015 (2015-09-13), XP055349551, Retrieved from the Internet &lt;URL:https://arxiv.org/abs/1506.08230v2&gt; [retrieved on 20170222]</text></B562><B562><text>Ç. GÜLÇEHRE ET AL: "Knowledge matters: importance of prior information for optimization", ARXIV:1301.4083V6, 13 July 2013 (2013-07-13), XP055266282, Retrieved from the Internet &lt;URL:https://arxiv.org/abs/1301.4083v6&gt; [retrieved on 20170222]</text></B562><B562><text>T. VATANEN ET AL: "Pushing stochastic gradient towards second-order methods - backpropagation learning with transformations in nonlinearities", LECTURE NOTES IN COMPUTER SCIENCE, vol. 8226, 3 November 2013 (2013-11-03), pages 442 - 449, XP047044497, DOI: 10.1007/978-3-642-42054-2_55</text></B562><B562><text>Y. GANIN, V. LEMPITSKY: "Unsupervised domain adaptation by backpropagation", JMLR WORKSHOP AND CONFERENCE PROCEEDINGS, vol. 37, 1 June 2015 (2015-06-01), pages 1180 - 1189, XP055349552, ISSN: 1938-7228</text></B562><B562><text>G. DESJARDINS ET AL: "Natural neural networks", ARXIV:1507.00210V1, 1 July 2015 (2015-07-01), XP055298466, Retrieved from the Internet &lt;URL:https://arxiv.org/abs/1507.00210v1&gt; [retrieved on 20170222]</text></B562><B562><text>S. IOFFE, C. SZEGEDY: "Batch normalization: accelerating deep network training by reducing internal covariate shift", ARXIV:1502.03167V3, 2 March 2015 (2015-03-02), XP055266268, Retrieved from the Internet &lt;URL:https://arxiv.org/abs/1502.03167v3&gt; [retrieved on 20170222]</text></B562></B560></B500><B700><B720><B721><snm>VAN HASSELT, Hado Philip</snm><adr><str>6 Pancras Square</str><city>London N1C 4AG</city><ctry>GB</ctry></adr></B721></B720><B730><B731><snm>DeepMind Technologies Limited</snm><iid>101864257</iid><irf>PX217504EP</irf><adr><str>5 New Street Square</str><city>London EC4A 3TW</city><ctry>GB</ctry></adr></B731></B730><B740><B741><snm>Marks &amp; Clerk GST</snm><iid>101982368</iid><adr><str>1 New York Street</str><city>Manchester M1 4HD</city><ctry>GB</ctry></adr></B741></B740></B700><B800><B840><ctry>AL</ctry><ctry>AT</ctry><ctry>BE</ctry><ctry>BG</ctry><ctry>CH</ctry><ctry>CY</ctry><ctry>CZ</ctry><ctry>DE</ctry><ctry>DK</ctry><ctry>EE</ctry><ctry>ES</ctry><ctry>FI</ctry><ctry>FR</ctry><ctry>GB</ctry><ctry>GR</ctry><ctry>HR</ctry><ctry>HU</ctry><ctry>IE</ctry><ctry>IS</ctry><ctry>IT</ctry><ctry>LI</ctry><ctry>LT</ctry><ctry>LU</ctry><ctry>LV</ctry><ctry>MC</ctry><ctry>MK</ctry><ctry>MT</ctry><ctry>NL</ctry><ctry>NO</ctry><ctry>PL</ctry><ctry>PT</ctry><ctry>RO</ctry><ctry>RS</ctry><ctry>SE</ctry><ctry>SI</ctry><ctry>SK</ctry><ctry>SM</ctry><ctry>TR</ctry></B840><B860><B861><dnum><anum>US2016061663</anum></dnum><date>20161111</date></B861><B862>en</B862></B860><B870><B871><dnum><pnum>WO2017083746</pnum></dnum><date>20170518</date><bnum>201720</bnum></B871></B870></B800></SDOBI>
</ep-patent-document>
