<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.0 20120330//EN" "JATS-journalpublishing1.dtd"><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article"><front><journal-meta><journal-id journal-id-type="publisher-id">INFORMATICA</journal-id><journal-title-group><journal-title>Informatica</journal-title></journal-title-group><issn pub-type="epub">0868-4952</issn><issn pub-type="ppub">0868-4952</issn><publisher><publisher-name>VU</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">inf14208</article-id><article-id pub-id-type="doi">10.15388/Informatica.2003.017</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research article</subject></subj-group></article-categories><title-group><article-title>Quick Training Algorithm for Extra Reduced Size Lattice‐Ladder Multilayer Perceptrons<xref ref-type="fn" rid="fn1"><sup>✩</sup></xref></article-title></title-group><contrib-group><contrib contrib-type="Author"><name><surname>Navakauskas</surname><given-names>Dalius</given-names></name><email xlink:href="mailto:dalius@el.vtu.lt">dalius@el.vtu.lt</email><xref ref-type="aff" rid="j_INFORMATICA_aff_000"/></contrib><aff id="j_INFORMATICA_aff_000">Department of Radioelectronics, Vilnius Gediminas Technical University, Naugarduko 41, LT‐2600 Vilnius, Lithuania</aff></contrib-group><author-notes><fn id="fn1"><label><sup>✩</sup></label><p>For the financial support author would like to thank prof. L. Ljung (Linköping University, Sweden), The Royal Swedish Academy of Sciences and The Swedish Institute – New Visby project Ref. No. 2473/2002 (381/T81).</p></fn></author-notes><pub-date pub-type="epub"><day>01</day><month>01</month><year>2003</year></pub-date><volume>14</volume><issue>2</issue><fpage>223</fpage><lpage>236</lpage><history><date date-type="received"><day>01</day><month>11</month><year>2002</year></date></history><abstract><p>A quick gradient training algorithm for a specific neural network structure called an extra reduced size lattice‐ladder multilayer perceptron is introduced. Presented derivation of the algorithm utilizes recently found by author simplest way of exact computation of gradients for rotation parameters of lattice‐ladder filter. Developed neural network training algorithm is optimal in terms of minimal number of constants, multiplication and addition operations, while the regularity of the structure is also preserved.</p></abstract><kwd-group><label>Keywords</label><kwd>lattice‐ladder filter</kwd><kwd>lattice‐ladder multilayer perceptron</kwd><kwd>adaptation</kwd><kwd>gradient adaptive lattice algorithms</kwd></kwd-group></article-meta></front></article>