<?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">izvestswsu</journal-id><journal-title-group><journal-title xml:lang="ru">Известия Юго-Западного государственного университета</journal-title><trans-title-group xml:lang="en"><trans-title>Proceedings of the Southwest State University</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2223-1560</issn><issn pub-type="epub">2686-6757</issn><publisher><publisher-name>ЮЗГУ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21869/2223-1560-2020-24-1-130-143</article-id><article-id custom-type="elpub" pub-id-type="custom">izvestswsu-726</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>Информатика, вычислительная техника и управление</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Computer science, computer engineering and IT managment</subject></subj-group></article-categories><title-group><article-title>Синтез архитектуры нейронной сети для распознавания образов морских судов</article-title><trans-title-group xml:lang="en"><trans-title>Synthesis of Neural Network Architecture for Recognition of Sea-Going Ship Images</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>Конарев</surname><given-names>Д. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Konarev</surname><given-names>D. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Конарев Дмитрий Игоревич, аспирант</p><p>ул. 50 лет Октября 94, г. Курск 305040</p></bio><bio xml:lang="en"><p>Dmitrii I. Konarev, Post-Graduate Student</p><p>50 Let Oktyabrya str. 94, Kursk 305040</p></bio><email xlink:type="simple">dmitrii.konarev@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гуламов</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Gulamov</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Гуламов Алишер Абдумаликович, доктор физико-математических наук, доцент, профессор кафедры КПиСС</p><p>ул. 50 лет Октября 94, г. Курск 305040</p></bio><bio xml:lang="en"><p>Alisher A. Gulamov, Dr. of Sci. (Engineering), Associate Professor</p><p>50 Let Oktyabrya str. 94, Kursk 305040</p></bio><email xlink:type="simple">profgulamov@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>ФГБОУ ВО «Юго-Западный государственный университет»</institution></aff><aff xml:lang="en"><institution>Southwest State University</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2020</year></pub-date><pub-date pub-type="epub"><day>23</day><month>06</month><year>2020</year></pub-date><volume>24</volume><issue>1</issue><fpage>130</fpage><lpage>143</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Конарев Д.И., Гуламов А.А., 2020</copyright-statement><copyright-year>2020</copyright-year><copyright-holder xml:lang="ru">Конарев Д.И., Гуламов А.А.</copyright-holder><copyright-holder xml:lang="en">Konarev D.I., Gulamov A.A.</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://izvestswsu.elpub.ru/jour/article/view/726">https://izvestswsu.elpub.ru/jour/article/view/726</self-uri><abstract><sec><title>Цель исследования</title><p>Цель исследования. В области инфокоммуникационного обеспечения судоходства Канала имени Москвы актуальной задачей является мониторинг судов с использованием камер видеонаблюдения, установленных на протяжении канала. Основной подзадачей является непосредственно распознавание судов на изображении или видео, для чего перспективно применение нейронной сети.</p></sec><sec><title>Методы</title><p>Методы. В работе рассмотрены различные архитектуры нейронной сети. Входными данными для сети являются изображения судов. Обучающая выборка использует набор данных CIFAR-10. Сеть построена и обучена с использованием библиотек машинного обучения Keras и TensorFlow.</p></sec><sec><title>Результаты</title><p>Результаты. Описано применение свёрточных искусственных нейронных сетей для задач распознавания образов и преимущества такой архитектуры при работе с изображениями. Обоснован выбор языка Python для реализации нейронной сети и описаны основные применяемые библиотеки машинного обучения, такие, как TensorFlow и Keras. Проведён эксперимент по обучению свёрточных нейронных сетей с различной архитектурой на базе сервиса Google collaboratoty. Проведена оценка эффективности различных архитектур в процентном соотношении случаев правильного распознавания образов на тестовой выборке. Сделаны выводы о влиянии параметров свёрточной нейронной сети на проявление её эффективности.</p></sec><sec><title>Заключение</title><p>Заключение. Сеть с одним свёрточным слоем в каждом каскаде показала недостаточные результаты, поэтому были рассмотрены трёхкаскадные свёрточные сети с двумя и тремя свёрточными слоями в каждом каскаде. Наибольшее влияние на точность распознавания образов оказало увеличение карты признаков. Наращивание числа каскадов оказало менее заметный эффект, а увеличение числа свёрточных слоёв в каждом каскаде не всегда приводит к повышению точности работы нейронной сети. В процессе исследования трёхкаcкадная сеть с двумя свёрточными слоями в каждом каскаде и 128 картами признаков определена как оптимальная архитектура нейронной сети в рассматриваемых условиях. Проверка работоспособности части рассматриваемых архитектур на случайных изображениях судов подтвердила правильность выбора оптимальной архитектуры.</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>Purpose of research</title><p>Purpose of research. The current task is to monitor ships using video surveillance cameras installed along the canal. It is important for information communication support for navigation of the Moscow Canal. The main subtask is direct recognition of ships in an image or video. Implementation of a neural network is perspectively.</p></sec><sec><title>Methods</title><p>Methods. Various neural network are described. images of ships are an input data for the network. The learning sample uses CIFAR-10 dataset. The network is built and trained by using Keras and TensorFlow machine learning libraries.</p></sec><sec><title>Results</title><p>Results. Implementation of curving artificial neural networks for problems of image recognition is described. Advantages of such architecture when working with images are also described. The selection of Python language for neural network implementation is justified. The main used libraries of machine learning, such as TensorFlow and Keras are described. An experiment has been conducted to train swirl neural networks with different architectures based on Google collaboratoty service. The effectiveness of different architectures was evaluated as a percentage of correct pattern recognition in the test sample. Conclusions have been drawn about parameters influence of screwing neural network on showing its effectiveness.</p></sec><sec><title>Conclusion</title><p>Conclusion. The network with a single curl layer in each cascade showed insufficient results, so three-stage curls with two and three curl layers in each cascade were used. Feature map extension has the greatest impact on the accuracy of image recognition. The increase in cascades' number has less noticeable effect and the increase in the number of screwdriver layers in each cascade does not always have an increase in the accuracy of the neural network. During the study, a three-frame network with two buckling layers in each cascade and 128 feature maps is defined as an optimal architecture of neural network under described conditions. operability checking of architecture's part under consideration on random images of ships confirmed the correctness of optimal architecture choosing.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>искусственные нейронные сети</kwd><kwd>свёрточная нейронная сеть</kwd><kwd>ядро свёртки</kwd><kwd>Keras</kwd><kwd>TensorFlow</kwd><kwd>Google collaboratoty</kwd><kwd>Cifar-10</kwd></kwd-group><kwd-group xml:lang="en"><kwd>artificial neural networks</kwd><kwd>convolutional neural network</kwd><kwd>convolution kernel</kwd><kwd>Keras</kwd><kwd>TensorFlow</kwd><kwd>Google collaboratoty</kwd><kwd>Cifar-10</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Гольцова И. А., Гуламов А. А. Информационное обеспечение участка железной дороги // Известия Юго-Западного государственного университета. Серия: Управление, вычислительная техника, информатика. Медицинское приборостроение. 2017. Т. 7, № 2(23). С. 6–11. https://swsu.ru/izvestiya/seriesivt/archiv/2_2017.pdf</mixed-citation><mixed-citation xml:lang="en">Gol'tsova I. A., Gulamov A. A. Informatsionnoe obespechenie uchastka zheleznoi dorogi [Information support of the railway section]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computing Engineering, Information Science. Medical Instruments Engineering, 2017, vol. 7, no. 2(23), pp. 6–11 (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Маклаков Е. С., Гуламов А.А. Узел сбора информации диспетчерского центра // Известия Юго-Западного государственного университета. 2018. Т. 22, № 6(81). С. 136-142. https://doi.org/10.21869/2223-1560-2018-22-6-136-142.</mixed-citation><mixed-citation xml:lang="en">Maklakov Ye. S., Gulamov A.A. Uzel sbora informatsii dispetcherskogo tsentra [The Collection of Information Control Center]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University, 2018, vol. 22, no. 6(81), pp. 136-142 (In Russ.). https://doi.org/10.21869/2223-1560-2018-22-6-136-142 (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Маклаков Е. С., Гуламов А.А. Оптимизация «последних миль» до удаленных узлов доступа путем применения технологии LCAS // Моделирование, оптимизация и информационные технологии: научный журнал. 2019. Т. 7. № 3. http://moit.vivt.ru/. https://doi.org/10.26102/2310-6018/2019.26.3.039.</mixed-citation><mixed-citation xml:lang="en">Maklakov Ye. S., Gulamov A.A. Optimizatsiya «poslednikh mil'» do udalennykh uzlov dostupa putem primeneniya tekhnologii LCAS [Optimization of "last miles" to remote access nodes by application of LCAS technology]. Modelirovaniye, optimizatsiya i informatsionnyye tekhnologii. Nauchnyy zhurnal = Modeling, optimization and information technology. Scientific journal, 2019, vol. 7, no. 3. https://doi.org/10.26102/2310-6018/2019.26.3.039 (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Видеосистема обнаружения морских судов по триангуляционным рашёткам / Ш. С. Фахми, Е. В. Костикова, М. С. Крюкова, С. А. Селиверстов // Морские интеллектуальные технологии. 2018. № 1-3 (41). С.143-155. http://morintex.ru/wpcontent/files_mf/1536237135MITVOL41No3PART12018compressed.pdf</mixed-citation><mixed-citation xml:lang="en">Fakhmi Sh. S., Kostikova E. V., Kryukova M. S., Seliverstov S. A. Videosistema obnaruzheniya morskikh sudov po triangulyatsionnym rashetkam [Video system for the detection of ships by triangulation grids]. Morskiye intellektual'nyye tekhnologii = Marine Intelligent Technology, 2018. no. 1-3 (41), pp.143-155. http://morintex.ru/wp-content/files_mf/1536237135MITVOL41No3PART12018compressed.pdf (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Фахми Ш. С., Шаталова Н. В., Крюкова М. С. Выделение контуров морских объектов на основе пирамидально-рекурсивного метода представления изображений // Морские интеллектуальные технологии. 2019. № 2-2 (44). С.129-136. http://morintex.ru/wp-content/files_mf/1560970718MITVOL44No2PART12019.pdf</mixed-citation><mixed-citation xml:lang="en">Fakhmi Sh. S., Shatalova N. V, Kryukova M. S. Vydelenie konturov morskikh ob"ektov na osnove piramidal'no-rekursivnogo metoda predstavleniya izobrazhenii [Isolation of the contours of marine objects based on the pyramidal-recursive image representation method]. Morskiye intellektual'nyye tekhnologii = Marine Intelligent Technology Publ., 2019, no. 2-2 (44), pp.129-136. http://morintex.ru/wp-content/files_mf/1560970718MITVOL44No2PART12019.pdf (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Выделение контуров изображений морских судов / Ш. С. Фахми, Н. В. Шаталова, С. А. Селиверстов, Е. С. Калинина, А. В. Иванов // Морские интеллектуальные технологии. 2019. № 3-3 (45). С.132-142. http://morintex.ru/wp-content/files_mf/1568625233MITVOL45No3PART32019_compressed1.pdf</mixed-citation><mixed-citation xml:lang="en">Fakhmi Sh. S., Shatalova N. V., Seliverstov S. A., Kalinina E. S., Ivanov A. V. Vydelenie konturov izobrazhenii morskikh sudov [Highlighting the contours of images of ships]. Morskiye intellektual'nyye tekhnologii = Marine Intelligent Technology. 2019, no. 3-3 (45), pp.132-142. http://morintex.ru/wp-content/files_mf/1568625233MITVOL45No3PART32019_compressed1.pdf (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Erhu Zhang, Kelu Wang, Guangfeng Lin Classification of marine vessels with multifeature structure fusion // Applied Science. 2019. № 9(10). Р. 2153. https://doi.org/10.3390/app9102153.</mixed-citation><mixed-citation xml:lang="en">Erhu Zhang, Kelu Wang, Guangfeng Lin Classification of marine vessels with multifeature structure fusion. Applied Science, 2019, no. 9(10), 2153 p. https://doi.org/10.3390/app9102153.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Tom Hope, Yehezkel S. Resheff, Itay Lieder Learning TensorFlow: A Guide to Building Deep Learning Systems O'Reilly Media; 1 edition, 2017. 242 p. https://www.oreilly.com/catalog/errata.csp?isbn=0636920044116</mixed-citation><mixed-citation xml:lang="en">Tom Hope, Yehezkel S. Resheff, Itay Lieder Learning TensorFlow: A Guide to Building Deep Learning Systems O'Reilly Media; 1 edition, 2017, 242 pp. https://www.oreilly.com/catalog/errata.csp?isbn=0636920044116.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Андреас Мюллер. Введение в машинное обучение с помощью Python. Руководство для специалистов по работе с данными. М.: Вильямс, 2017. 480 с. https://codernet.ru/books/python/vvedenie_v_mashinnoe_obuchenie_s_pomoshhyu_python/</mixed-citation><mixed-citation xml:lang="en">Andreas Myuller. Vvedenie v mashinnoe obuchenie s pomoshch'yu Python [Introduction to machine learning with Python. Guide for data professionals]. Moscow, Vil'yams Publ., 2017, 480 p. https://codernet.ru/books/python/vvedenie_v_mashinnoe_obuchenie_s_pomoshhyu_python/ (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Себастьян Рашка. Python и машинное обучение. М.: ДМК-Пресс, 2017. 418 с.</mixed-citation><mixed-citation xml:lang="en">Sebast'yan Rashka. Python i mashinnoe obuchenie [Python and machine learning]. Moscow, DMK-Press Publ., 2017. 418 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng, Google Brain Tensor flow: A system for large-scale machine learning // Operating Systems Design and Implementation: Proc. 12th Symposium, Savannah, GA, USA, 2016. pp. 265-283. https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf</mixed-citation><mixed-citation xml:lang="en">Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng, Google Brain Tensor flow: A system for large-scale machine learning. Operating Systems Design and Implementation: Proc. 12th Symposium, Savannah, GA, USA, 2016, pp. 265-283. https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Антонио Джулли, Суджит Пал. Библиотека Keras – инструмент глубокого обучения. Реализация нейронных сетей с помощью библиотек Theano и Tensor Flow. М.: ДМК-Пресс, 2017. 296 с.</mixed-citation><mixed-citation xml:lang="en">Antonio Dzhulli, Sudzhit Pal. Biblioteka Keras – instrument glubokogo obu-cheniya. Realizatsiya neironnykh setei s pomoshch'yu bibliotek Theano i Tensor Flow [Keras Library is a deep learning tool. Implementing neural networks using Theano and Tensor Flow libraries.]. Moscow, DMK-Press Publ., 2017, 296 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Франсуа Шолле. Глубокое обучение на Python. СПб.: Питер, 2018. 400 с.</mixed-citation><mixed-citation xml:lang="en">Fransua Sholle. Glubokoe obuchenie na Python [Python Deep Learning]. SaintPetersburg, Piter Publ., 2018. 400 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Aurélien Géron, Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems O'Reilly Media, 2017. 574 p. https://www.academia.edu/37010160/Hands-On_Machine_Learning_with_Scikit-Learn_and_TensorFlow.</mixed-citation><mixed-citation xml:lang="en">Aurélien Géron, Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems O'Reilly Media, 2017. 574 p. https://www.academia.edu/37010160/Hands-On_Machine_Learning_with_Scikit-Learn_and_TensorFlow.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Ian Goodfellow, Deep Learning (Adaptive Computation and Machine Learning series) The MIT Press, 2016. 800 p. https://www.academia.edu/38223830/Adaptive_Computation_and_Machine_Learning_series-_Deep_learning-The_MIT_Press_2016_.pdf</mixed-citation><mixed-citation xml:lang="en">Ian Goodfellow, Deep Learning (Adaptive Computation and Machine Learning series) The MIT Press, 2016. 800 p. https://www.academia.edu/38223830/Adaptive_Computation_and_Machine_Learning_series-_Deep_learning-The_MIT_Press_2016_.pdf</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Tariq Rashid, Make Your Own Neural Network CreateSpace Independent Publishing Platform, 2016. 222 p.</mixed-citation><mixed-citation xml:lang="en">Tariq Rashid, Make Your Own Neural Network CreateSpace Independent Publishing Platform, 2016, 222 p.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Schmidhuber J. Deep learning in neural networks: An overview // Neural Networks. 2015. Vol. (61). P. 85–117. http://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf</mixed-citation><mixed-citation xml:lang="en">Schmidhuber J. Deep learning in neural networks: An overview Neural Networks. 2015, vol. (61), pp. 85–117. http://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Josh Patterson, Adam Gibson Deep Learning: A Practitioner's Approach O'Reilly Media, Inc. 2017. 532 p. https://www.academia.edu/37119738/Deep_Learning_A_Practitioners_Approach</mixed-citation><mixed-citation xml:lang="en">Josh Patterson, Adam Gibson Deep Learning: A Practitioner's Approach O'Reilly Media, Inc. 2017, 532 p. https://www.academia.edu/37119738/Deep_Learning_A_Practitioners_Approach.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Саймон Хайкин. Нейронные сети. М.: Вильямс, 2018. 1104 с.</mixed-citation><mixed-citation xml:lang="en">Saimon Khaikin. Neironnye seti [Neural networks]. Moscow, Vil'yams Publ., 2018, 1104 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Michael Taylor The Math of Neural Networks Amazon Digital Services LLC - Kdp Print Us, 2017. 168 p. https://cours.etsmtl.ca/sys843/REFS/Books/ebook_Haykin09.pdf</mixed-citation><mixed-citation xml:lang="en">Michael Taylor The Math of Neural Networks Amazon Digital Services LLC - Kdp Print Us, 2017. 168 p. https://cours.etsmtl.ca/sys843/REFS/Books/ebook_Haykin09.pdf</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>
