<?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">procyber</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник кибернетики</journal-title><trans-title-group xml:lang="en"><trans-title>Proceedings in Cybernetics</trans-title></trans-title-group></journal-title-group><issn pub-type="epub">1999-7604</issn><publisher><publisher-name>Бюджетное учреждение высшего образования Ханты-Мансийского автономного округа – Югры «Сургутский государственный университет»</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.34822/1999-7604-2020-2-20-31</article-id><article-id custom-type="elpub" pub-id-type="custom">procyber-294</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>ТЕХНИЧЕСКИЕ НАУКИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Engeneering</subject></subj-group></article-categories><title-group><article-title>ВЕЙВЛЕТ-ПОДОБНАЯ АРХИТЕКТУРА КОМПЛЕКСНОЗНАЧНОЙ СВЕРТОЧНОЙ НЕЙРОННОЙ СЕТИ ДЛЯ СИНТЕЗА КОМПЛЕКСНЫХ СИГНАЛОВ</article-title><trans-title-group xml:lang="en"><trans-title>WAVELET-LIKE ARCHITECTURE OF COMPLEX-VALUED CONVOLUTIONAL NEURAL NETWORK FOR COMPLEX SIGNAL SYNTHESIS</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>Караваев</surname><given-names>Д. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Karavaev</surname><given-names>D. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>E-mail: d.a.karavaev@yandex.ru</p></bio><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный университет телекоммуникаций им. проф. М. А. Бонч-Бруевича, Санкт-Петербург</institution></aff><aff xml:lang="en"><institution>Bonch-Bruevich Saint-Petersburg State University of Telecommunications, Saint Petersburg</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2020</year></pub-date><pub-date pub-type="epub"><day>31</day><month>07</month><year>2020</year></pub-date><volume>0</volume><issue>2 (38)</issue><fpage>20</fpage><lpage>31</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Караваев Д.А., 2020</copyright-statement><copyright-year>2020</copyright-year><copyright-holder xml:lang="ru">Караваев Д.А.</copyright-holder><copyright-holder xml:lang="en">Karavaev D.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://www.vestcyber.ru/jour/article/view/294">https://www.vestcyber.ru/jour/article/view/294</self-uri><abstract><p>В работе предложена архитектура комплекснозначной сверточной нейронной сети, разработанная на основе структуры дискретного вейвлет-преобразования. Данная архитектура позволяет производить многоуровневую декомпозицию комплексного сигнала, формируя набор признаков, который можно применять для задач синтеза и классификации сигналов. Приведены результаты решения задачи предсказания значений хаотического комплексного сигнала нейронной сетью, основанные на предлагаемой архитектуре. Полученные результаты сравниваются с результатами решения данной задачи при помощи вещественнозначных нейросетевых моделей, основанными на альтернативных современных подходах. Также проведен анализ представленной комплекснозначной сверточной сети в частотной области, осуществленный за счет сравнительно небольшого числа адаптивных параметров.</p></abstract><trans-abstract xml:lang="en"><p>The paper proposes the architecture of a complex-valued convolutional neural network, built upon a structure of the discrete wavelet transform. This architecture allows performing multiscale decomposition of a complex signal, thus forming a set of features that can be used for the tasks of signal synthesis and classification. The article presents the results of solving the prediction problem for the values of a chaotic complex signal by a neural network based on the proposed architecture.The obtained results are compared with the results of solving this problem using real-valued neural networks based on alternative modern approaches. The analysis of the presented complex-valued convolutional network in the frequency domain is also carried out, which was achieved due to a relatively small number of adaptive parameters.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>цифровая обработка сигналов</kwd><kwd>машинное обучение</kwd><kwd>комплескнозначные нейронные сети</kwd><kwd>вейвлет-преобразование</kwd><kwd>прогнозирование временных рядов.</kwd></kwd-group><kwd-group xml:lang="en"><kwd>digital signal processing</kwd><kwd>machine learning</kwd><kwd>complex-valued neural networks</kwd><kwd>wavelet transform</kwd><kwd>time series forecasting.</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">LeCun Y., Bengio Y., Hinton G. E. Deep Learning // Nature. 2015. Vol. 521, No. 7553. P. 436–444. DOI: https://doi.org/10.1038/nature14539.</mixed-citation><mixed-citation xml:lang="en">LeCun Y., Bengio Y., Hinton G. E. Deep Learning // Nature. 2015. Vol. 521, No. 7553. P. 436–444. DOI: https://doi.org/10.1038/nature14539.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Джиган В. И. Адаптивные фильтры и их приложения в радиотехнике и связи. Ч. 3 // Соврем. электроника. 2010. Т. 2. С. 70–77.</mixed-citation><mixed-citation xml:lang="en">Джиган В. И. Адаптивные фильтры и их приложения в радиотехнике и связи. Ч. 3 // Соврем. электроника. 2010. Т. 2. С. 70–77.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Hirose A. Complex-Valued Neural Networks. Studies in computational intelligence. Springer-Verlag, 2006. URL: https://books.google.ru/books?id=d2INKuuzQjEC (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Hirose A. Complex-Valued Neural Networks. Studies in computational intelligence. Springer-Verlag, 2006. URL: https://books.google.ru/books?id=d2INKuuzQjEC (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Chiheb T., Bilaniuk O., Serdyuk D., et al. Deep Complex Networks // CoRR. 2017. URL: http://arxiv.org/abs/1705.09792 (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Chiheb T., Bilaniuk O., Serdyuk D., et al. Deep Complex Networks // CoRR. 2017. URL: http://arxiv.org/abs/1705.09792 (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Ioffe S., Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift // CoRR. 2015. URL: http://arxiv.org/abs/1502.03167 (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Ioffe S., Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift // CoRR. 2015. URL: http://arxiv.org/abs/1502.03167 (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Bruna J., Chintala S., LeCun Y., et al. A Theoretical Argument for Complex-Valued Convolutional Networks // CoRR. 2015. URL: http://arxiv.org/abs/1503.03438 (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Bruna J., Chintala S., LeCun Y., et al. A Theoretical Argument for Complex-Valued Convolutional Networks // CoRR. 2015. URL: http://arxiv.org/abs/1503.03438 (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Theano Development Team. Theano: A Python framework for fast computation of mathematical expressions // arXiv e-prints. 2016. URL: http://arxiv.org/abs/1605.02688 (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Theano Development Team. Theano: A Python framework for fast computation of mathematical expressions // arXiv e-prints. 2016. URL: http://arxiv.org/abs/1605.02688 (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Keras: the Python deep learning API. URL: https://keras.io. (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Keras: the Python deep learning API. URL: https://keras.io. (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Hunter J. D. Matplotlib: A 2D Graphics Environment // Computing in Science &amp; Engineering. 2007. Vol. 9, No. 3. P. 90–95.</mixed-citation><mixed-citation xml:lang="en">Hunter J. D. Matplotlib: A 2D Graphics Environment // Computing in Science &amp; Engineering. 2007. Vol. 9, No. 3. P. 90–95.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Yu F., Koltun V. Multi-Scale Context Aggregation by Dilated Convolutions // CoRR. 2015. URL: http://arxiv.org/abs/1511.07122 (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Yu F., Koltun V. Multi-Scale Context Aggregation by Dilated Convolutions // CoRR. 2015. URL: http://arxiv.org/abs/1511.07122 (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Santurkar S., Tsipras D., Ilyas A., et al. How Does Batch Normalization Help Optimization? // Advances in Neural Information Processing Systems. 2018. Vol. 31, P. 2483–2493.</mixed-citation><mixed-citation xml:lang="en">Santurkar S., Tsipras D., Ilyas A., et al. How Does Batch Normalization Help Optimization? // Advances in Neural Information Processing Systems. 2018. Vol. 31, P. 2483–2493.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Clevert D. A., Unterthiner T., Hochreiter S. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) // CoRR. 2015. URL: http://arxiv.org/abs/1511.07289 (дата</mixed-citation><mixed-citation xml:lang="en">Clevert D. A., Unterthiner T., Hochreiter S. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) // CoRR. 2015. URL: http://arxiv.org/abs/1511.07289 (дата</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Arjovsky M., Shah A., Bengio Y. Unitary Evolution Recurrent Neural Networks // CoRR. 2015. URL: http://arxiv.org/abs/1511.06464 (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Arjovsky M., Shah A., Bengio Y. Unitary Evolution Recurrent Neural Networks // CoRR. 2015. URL: http://arxiv.org/abs/1511.06464 (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Mallat S. A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way. Orlando, FL, USA : Academic Press, Inc., 2008.</mixed-citation><mixed-citation xml:lang="en">Mallat S. A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way. Orlando, FL, USA : Academic Press, Inc., 2008.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, 2016.</mixed-citation><mixed-citation xml:lang="en">Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, 2016.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">He K., Zhang X., Ren S. et al. Deep Residual Learning for Image Recognition // CoRR. 2015. URL: http://arxiv.org/abs/1512.03385 (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">He K., Zhang X., Ren S. et al. Deep Residual Learning for Image Recognition // CoRR. 2015. URL: http://arxiv.org/abs/1512.03385 (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Van den Oord A., Dieleman S., Zen H., et al. WaveNet: A Generative Model for Raw Audio // CoRR. 2016. URL: http://arxiv.org/abs/1609.03499 (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Van den Oord A., Dieleman S., Zen H., et al. WaveNet: A Generative Model for Raw Audio // CoRR. 2016. URL: http://arxiv.org/abs/1609.03499 (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Borovykh A., Bohte S. M., Oosterlee C. W. Conditional Time Series Forecasting with Convolutional Neural Networks // CoRR. 2017. URL: http://arxiv.org/abs/1703.04691 (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Borovykh A., Bohte S. M., Oosterlee C. W. Conditional Time Series Forecasting with Convolutional Neural Networks // CoRR. 2017. URL: http://arxiv.org/abs/1703.04691 (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Dozat T. Incorporating Nesterov Momentum into Adam // Workshop track – ICLR. 2016. URL: https://openreview.net/pdf?id=OM0jvwB8jIp57ZJjtNEZ (дата обращения: 30.04.2020).</mixed-citation><mixed-citation xml:lang="en">Dozat T. Incorporating Nesterov Momentum into Adam // Workshop track – ICLR. 2016. URL: https://openreview.net/pdf?id=OM0jvwB8jIp57ZJjtNEZ (дата обращения: 30.04.2020).</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Glorot X., Bengio Y. Understanding the Difficulty of Training Deep Feedforward Neural Networks // Proceedings of the International Conference on Artificial Intelligence and Statistics</mixed-citation><mixed-citation xml:lang="en">Glorot X., Bengio Y. Understanding the Difficulty of Training Deep Feedforward Neural Networks // Proceedings of the International Conference on Artificial Intelligence and Statistics</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">(AISTATS’10) : Society for Artificial Intelligence and Statistics. 2010.</mixed-citation><mixed-citation xml:lang="en">(AISTATS’10) : Society for Artificial Intelligence and Statistics. 2010.</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Ikeda K. Multiple-Valued Stationary State and its Instability of the Transmitted Light by a Ring Cavity System // Optics Communications. 1979. Vol. 30, No. 2. P. 257–261.</mixed-citation><mixed-citation xml:lang="en">Ikeda K. Multiple-Valued Stationary State and its Instability of the Transmitted Light by a Ring Cavity System // Optics Communications. 1979. Vol. 30, No. 2. P. 257–261.</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Mandic D. P., Still S., Douglas S. C. Duality between Widely Linear and Dual Channel Adaptive Filtering // 2009 IEEE International Conference on Acoustics, Speech and Signal Processing. 2009. P. 1729–1732.</mixed-citation><mixed-citation xml:lang="en">Mandic D. P., Still S., Douglas S. C. Duality between Widely Linear and Dual Channel Adaptive Filtering // 2009 IEEE International Conference on Acoustics, Speech and Signal Processing. 2009. P. 1729–1732.</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Hochreiter S., Schmidhuber J. Long Short-Term Memory // Neural Computation. 1997. Vol. 9, No. 8. P. 1735–1780.</mixed-citation><mixed-citation xml:lang="en">Hochreiter S., Schmidhuber J. Long Short-Term Memory // Neural Computation. 1997. Vol. 9, No. 8. P. 1735–1780.</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Rusch L. A., Poor H. V. Narrowband Interference Suppression in CDMA Spread Spectrum Communications // IEEE Transactions on Communications. 1994. Vol. 42, No. 234. P. 1969–1979.</mixed-citation><mixed-citation xml:lang="en">Rusch L. A., Poor H. V. Narrowband Interference Suppression in CDMA Spread Spectrum Communications // IEEE Transactions on Communications. 1994. Vol. 42, No. 234. P. 1969–1979.</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>
