<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">inform</journal-id><journal-title-group><journal-title xml:lang="ru">Информатика</journal-title><trans-title-group xml:lang="en"><trans-title>Informatics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1816-0301</issn><issn pub-type="epub">2617-6963</issn><publisher><publisher-name>UIIP NASB</publisher-name></publisher></journal-meta><article-meta><article-id custom-type="elpub" pub-id-type="custom">inform-680</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>МАТЕМАТИЧЕСКОЕ МОДЕЛИРОВАНИЕ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>MATHEMATICAL MODELING</subject></subj-group></article-categories><title-group><article-title>ГЛОБАЛЬНЫЙ АТТРАКТОР И ДОСТАТОЧНЫЕ УСЛОВИЯ ДЛЯ ВОССТАНОВЛЕНИЯ ОБРАЗОВ НЕЙРОСЕТЯМИ КОЭНА – ГРОССБЕРГА</article-title><trans-title-group xml:lang="en"><trans-title></trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Картынник</surname><given-names>А. В.</given-names></name></name-alternatives><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Линкевич</surname><given-names>А. Д.</given-names></name></name-alternatives><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff xml:lang="ru" id="aff-1"><institution>Полоцкий государственный университет</institution><country>Belarus</country></aff><pub-date pub-type="collection"><year>2006</year></pub-date><pub-date pub-type="epub"><day>07</day><month>12</month><year>2018</year></pub-date><volume>0</volume><issue>1(9)</issue><fpage>114</fpage><lpage>123</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Картынник А.В., Линкевич А.Д., 2018</copyright-statement><copyright-year>2018</copyright-year><copyright-holder xml:lang="ru">Картынник А.В., Линкевич А.Д.</copyright-holder><copyright-holder xml:lang="en">Картынник А.В., Линкевич А.Д.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://inf.grid.by/jour/article/view/680">https://inf.grid.by/jour/article/view/680</self-uri><abstract><p>Аналоговые нейронные сети Коэна – Гроссберга изучаются в общем случае, когда межнейронные (синаптические) связи могут быть несимметричными и, следовательно, отсутствует аналог гамильтониана для системы в полном фазовом пространстве (глобальная функция Ляпунова). Доказывается, что при определенных условиях существует глобальная притягивающая область Q, такая, что все аттракторы лежат внутри Q и, кроме того, область Q является аттрактором системы. Находится верхняя оценка времени, необходимого для достижения предписанной окрестности области Q. Получаются достаточные условия, при выполнении которых нейросеть асимптотически сходится к ближайшему стационарному состоянию (запомненному образу) и достигает заданной окрестности аттрактора системы за определенное (конечное) время. Находится верхняя граница времени, необходимого для восстановления запомненного образа с заданной точностью.</p></abstract></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Hopfield. J.J. Neural Networks and Physical Systems with Emergent Collective Computational Abilities // Proc. Natl. Acad. Sci. USA. – 1984. – Vol. 79. – P. 2554–2558.</mixed-citation><mixed-citation xml:lang="en">Hopfield. J.J. Neural Networks and Physical Systems with Emergent Collective Computational Abilities // Proc. Natl. Acad. Sci. USA. – 1984. – Vol. 79. – P. 2554–2558.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Cohen M.A., Grossberg S. Absolute Stability of Global Pattern Formation and Parallel Memory Storage by Competitive Neural Networks // IEEE Trans. Syst., Man, Cybern. – 1983. – Vol. SMS-13. – P. 815–826.</mixed-citation><mixed-citation xml:lang="en">Cohen M.A., Grossberg S. Absolute Stability of Global Pattern Formation and Parallel Memory Storage by Competitive Neural Networks // IEEE Trans. Syst., Man, Cybern. – 1983. – Vol. SMS-13. – P. 815–826.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Hopfield J.J. Neurons with Graded Response Have Collective Computational Properties Like those of Two. – State Neurons // Proc. Natl. Acad. Sci. USA. – 1984. – Vol. 81. – P. 3088–3092.</mixed-citation><mixed-citation xml:lang="en">Hopfield J.J. Neurons with Graded Response Have Collective Computational Properties Like those of Two. – State Neurons // Proc. Natl. Acad. Sci. USA. – 1984. – Vol. 81. – P. 3088–3092.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Pineda F.J. Generalization of Back – Propagation to Recurrent Neural Networks // Phys. Rev. Lett. – 1987. – Vol. 59. – P. 2229–2232.</mixed-citation><mixed-citation xml:lang="en">Pineda F.J. Generalization of Back – Propagation to Recurrent Neural Networks // Phys. Rev. Lett. – 1987. – Vol. 59. – P. 2229–2232.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Linkevich A.D. Learning neural networks with the aid of projection techniques // Proc. Second Seminar «Nonlinear Phenomena in Complex Systems», Polatsk, February 15–17, 1993. – Sant-Peterburg, 1993. – P. 373–382.</mixed-citation><mixed-citation xml:lang="en">Linkevich A.D. Learning neural networks with the aid of projection techniques // Proc. Second Seminar «Nonlinear Phenomena in Complex Systems», Polatsk, February 15–17, 1993. – Sant-Peterburg, 1993. – P. 373–382.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Linkevich A.D. A sequential learning rule for analogous neural networks // Optical Memory and Neural Networks. – 1993. – Vol. 2. – № 2. – P. 111–116.</mixed-citation><mixed-citation xml:lang="en">Linkevich A.D. A sequential learning rule for analogous neural networks // Optical Memory and Neural Networks. – 1993. – Vol. 2. – № 2. – P. 111–116.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Linkevich A.D. Projection learning algorithms for analog neural networks without self-action // Proc. Workshop «Mind, Brain and Neurocomputers», Minsk, November 16–18, 1993 // Advances in Synergetics. Vol. 1. – Minsk: Belarusian State Univ. Press, 1994. – P. 147–153.</mixed-citation><mixed-citation xml:lang="en">Linkevich A.D. Projection learning algorithms for analog neural networks without self-action // Proc. Workshop «Mind, Brain and Neurocomputers», Minsk, November 16–18, 1993 // Advances in Synergetics. Vol. 1. – Minsk: Belarusian State Univ. Press, 1994. – P. 147–153.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Kartynnick A.V., Linkevich A.D. Retrieval of memorized patterns by non-symmetric neural networks: Local Lyapunov functions and local contracting maps methods // Optical Memory and Neural Networksю – 1994. – Vol. 3. – № 3. – P. 329–342.</mixed-citation><mixed-citation xml:lang="en">Kartynnick A.V., Linkevich A.D. Retrieval of memorized patterns by non-symmetric neural networks: Local Lyapunov functions and local contracting maps methods // Optical Memory and Neural Networksю – 1994. – Vol. 3. – № 3. – P. 329–342.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Eccles J.C. Physiology of Synapses. – Berlin: Springer, 1964.</mixed-citation><mixed-citation xml:lang="en">Eccles J.C. Physiology of Synapses. – Berlin: Springer, 1964.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Das II P.K., Schieve W.C., Zeng Z.J. Сhaos in an Effective Four-Neuron Neural Net-works // Phys. Lett A. – 1991. – Vol. 161. – P. 60–66.</mixed-citation><mixed-citation xml:lang="en">Das II P.K., Schieve W.C., Zeng Z.J. Сhaos in an Effective Four-Neuron Neural Net-works // Phys. Lett A. – 1991. – Vol. 161. – P. 60–66.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Linkevich A.D. Mathematical Methods and Models for Investigation of Neurodynamical Mechanisms of Cognitive Processes. – Minsk: IEC NAS RB, 2001.</mixed-citation><mixed-citation xml:lang="en">Linkevich A.D. Mathematical Methods and Models for Investigation of Neurodynamical Mechanisms of Cognitive Processes. – Minsk: IEC NAS RB, 2001.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Шилов Г.Е. Математический анализ (функции одного переменного). Ч. 1. – М.: Наука, 1969.</mixed-citation><mixed-citation xml:lang="en">Шилов Г.Е. Математический анализ (функции одного переменного). Ч. 1. – М.: Наука, 1969.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Чаплыгин С.А. Собрание работ. Т. 1. – М.–Л.: Гостехиздат, 1948.</mixed-citation><mixed-citation xml:lang="en">Чаплыгин С.А. Собрание работ. Т. 1. – М.–Л.: Гостехиздат, 1948.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Арнольд В.И. Обыкновенные дифференциальные уравнения. – М.: Наука, 1971.</mixed-citation><mixed-citation xml:lang="en">Арнольд В.И. Обыкновенные дифференциальные уравнения. – М.: Наука, 1971.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
