<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article 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" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">RUDN Journal of Engineering Research</journal-id><journal-title-group><journal-title xml:lang="en">RUDN Journal of Engineering Research</journal-title><trans-title-group xml:lang="ru"><trans-title>Вестник Российского университета дружбы народов. Серия: Инженерные исследования</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2312-8143</issn><issn publication-format="electronic">2312-8151</issn><publisher><publisher-name xml:lang="en">Peoples’ Friendship University of Russia named after Patrice Lumumba (RUDN University)</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">31240</article-id><article-id pub-id-type="doi">10.22363/2312-8143-2022-23-1-7-14</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>Articles</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Статьи</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Evaluation criterion of the neural network model of heterostructural nanoelectronic devices for predicting their electrical parameters</article-title><trans-title-group xml:lang="ru"><trans-title>Критерий оценки нейросетевой модели гетероструктурных наноэлектронных устройств для прогнозирования их электрических параметров</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-6218-4111</contrib-id><name-alternatives><name xml:lang="en"><surname>Vetrova</surname><given-names>Natalia A.</given-names></name><name xml:lang="ru"><surname>Ветрова</surname><given-names>Наталия Алексеевна</given-names></name></name-alternatives><bio xml:lang="en"><p>Candidate of Technical Sciences, Associate Professor of the Department of Instrument Engineering Technologies, Bauman Moscow State Technical University (National Research University of Technology), ; Associate Professor of the Department of Nanotechnology and Microsystems Engineering, Academy of Engineering, Peoples’ Friendship University of Russia (RUDN University)</p></bio><bio xml:lang="ru"><p>кандидат технических наук, доцент кафедры «Технологии приборостроения», Московский государственный технический университет имени Н.Э. Баумана (национальный исследовательский университет); доцент кафедры нанотехнологий и микросистемной техники, Инженерная академия, Российский университет дружбы народов</p></bio><email>vetrova@bmstu.ru</email><xref ref-type="aff" rid="aff1"/><xref ref-type="aff" rid="aff2"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-7319-8001</contrib-id><name-alternatives><name xml:lang="en"><surname>Filyaev</surname><given-names>Alexandr A.</given-names></name><name xml:lang="ru"><surname>Филяев</surname><given-names>Александр Александрович</given-names></name></name-alternatives><bio xml:lang="en"><p>master student, Department of Instrument Engineering Technologies, Bauman Moscow State Technical University (National Research University of Technology), ; engineer of the scientific project, National Technology Initiative Center for Quantum Communications, National University of Science and Technology “MISIS,”</p></bio><bio xml:lang="ru"><p>магистрант, кафедра «Технологии приборостроения», Московский государственный технический университет имени Н.Э. Баумана (национальный исследовательский университет); инженер научного проекта, лаборатория квантовых коммуникаций, Национальный исследовательский технологический университет «МИСиС»</p></bio><email>alex.filyaev.98@gmail.com</email><xref ref-type="aff" rid="aff1"/><xref ref-type="aff" rid="aff3"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Bauman Moscow State Technical University (National Research University of Technology)</institution></aff><aff><institution xml:lang="ru">Московский государственный технический университет имени Н.Э. Баумана (национальный исследовательский университет)</institution></aff></aff-alternatives><aff-alternatives id="aff2"><aff><institution xml:lang="en">Peoples’ Friendship University of Russia (RUDN University)</institution></aff><aff><institution xml:lang="ru">Российский университет дружбы народов</institution></aff></aff-alternatives><aff-alternatives id="aff3"><aff><institution xml:lang="en">National University of Science and Technology “MISIS”</institution></aff><aff><institution xml:lang="ru">Национальный исследовательский технологический университет «МИСиС»</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2022-06-19" publication-format="electronic"><day>19</day><month>06</month><year>2022</year></pub-date><volume>23</volume><issue>1</issue><issue-title xml:lang="en">VOL 23, NO1 (2022)</issue-title><issue-title xml:lang="ru">ТОМ 23, №1 (2022)</issue-title><fpage>7</fpage><lpage>14</lpage><history><date date-type="received" iso-8601-date="2022-06-19"><day>19</day><month>06</month><year>2022</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2022, Vetrova N.A., Filyaev A.A.</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2022, Ветрова Н.А., Филяев А.А.</copyright-statement><copyright-year>2022</copyright-year><copyright-holder xml:lang="en">Vetrova N.A., Filyaev A.A.</copyright-holder><copyright-holder xml:lang="ru">Ветрова Н.А., Филяев А.А.</copyright-holder><ali:free_to_read xmlns:ali="http://www.niso.org/schemas/ali/1.0/"/><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">http://creativecommons.org/licenses/by/4.0</ali:license_ref></license></permissions><self-uri xlink:href="https://journals.rudn.ru/engineering-researches/article/view/31240">https://journals.rudn.ru/engineering-researches/article/view/31240</self-uri><abstract xml:lang="en"><p style="text-align: justify;">The paper is devoted to the neural network approach, which is proposed to be used to predict the operational parameters of heterostructural nanoscale devices. The advantage of this approach is a clear methodology for evaluating the weighting coefficients as part of a trained artificial neural network, which makes it possible to solve the problem for devices with an arbitrary structure. Learning is a complex iterative process, at the end of which it is important to evaluate the functioning of the neural network model. Therefore, it is necessary to determine the achieved accuracy and to identify negative effects that may occur during the learning process, when such a model is being developed. The project presents a criterion for evaluation the training quality of the neural network model of heterostructural nanoelectronic devices for predicting their electrical parameters. The main advantage of this criterion is its sensitivity to negative effects arising in the learning process, which was demonstrated by an example with two input training parameters and confirmed by visual control of 3D surfaces. The applicability of the developed criterion in the selection of neural networks with arbitrary architecture for solving design problems in the development of semi-conductor devices has been proved.</p></abstract><trans-abstract xml:lang="ru"><p style="text-align: justify;">Работа посвящена нейросетевому подходу, который предлагается использовать для прогнозирования эксплуатационных параметров гетероструктурных наноразмерных устройств различного назначения. Его преимуществом является эффективная методика оценки весовых коэффициентов в составе обучаемой искусственной нейронной сети, что позволяет решать задачу для устройств с произвольной структурой. Обучение представляет собой сложный итерационный процесс, по окончании которого важно производить оценку работы нейросетевой модели. Поэтому после построения такой модели необходимо определить достигаемую точность, а также выявить негативные эффекты, которые могут возникнуть в процессе обучения, в частности переобучение и недообучение сети. Представлен критерий оценки качества обучения нейросетевой модели гетероструктурных наноэлектронных устройств для прогнозирования их электрических параметров. Основное преимущество данного критерия - его чувствительность к негативным эффектам, возникающим в процессе обучения, что было продемонстрированно на примере с двумя входными обучающими параметрами и подтверждено визуальным контролем 3D-поверхностей. Доказана применимость разработанного критерия при выборе нейронных сетей с произвольной архитектурой для решения конструкторских задач при проектировании полупроводниковых приборов.</p></trans-abstract><kwd-group xml:lang="en"><kwd>nanoelectronics</kwd><kwd>criterion</kwd><kwd>artificial neural networks</kwd><kwd>heterostructural devices</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>наноэлектроника</kwd><kwd>критерий</kwd><kwd>искусственные нейронные сети</kwd><kwd>гетероструктурные устройства</kwd></kwd-group><funding-group/></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><mixed-citation>Manh LD, Diebold S, Nishio K, Nishida Y, Kim J, Mukai T, Fujita M, Nagatsuma T. External feedback effect in terahertz resonant tunneling diode oscillators. IEEE Transactions on Terahertz Science and Technology. 2018;8(4): 455-464. https://doi.org/10.1109/TTHZ.2018.2842209</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation>Kasagi K, Suzuki S, Asada M. Large-scale array of resonant-tunneling-diode terahertz oscillators for high output power at 1 THz. Journal of Applied Physics. 2019;125(15):151601. https://doi.org/10.1063/1.5051007</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation>Sattari-Esfahlan SM. Multi-peak negative differential resistance in silicene superlattice: Toward multi-valued silicene logic devices. Journal of Applied Physics. 2018;123(24):244503. https://doi.org/10.1063/1.5032122</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation>Fujita K, Jung S, Jiang Y, Kim JH, Nakanishi A, Ito A, Hitaka M, Edamura T, Belkin MA. Recent progress in terahertz difference-frequency quantum cascade laser sources. Nanophotonics. 2018;7(11):1795-1817. https://doi.org/10.1515/nanoph-2018-0093</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation>Rakić AD, Taimre T, Bertling K, Lim YL, Dean P, Valavanis A, Indjin D. Sensing and imaging using laser feedback interferometry with quantum cascade lasers. Applied Physics Reviews. 2019;6(2):021320. https://doi.org/10.1063/1.5094674</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation>Bosco L, Franckié M, Scalari G, Beck M, Wacker A, Faist J. Thermoelectrically cooled THz quantum cascade laser operating up to 210 K. Applied Physics Letters. 2019;115(1):010601. https://doi.org/10.1063/1.5110305</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation>de Oliveira ERC, Pfenning A, Castro EDG, Teodoro MD, dos Santos EC, Lopez-Richard V, Marques GE, Worschech L, Hartmann F, Höfling S. Electroluminescence on-off ratio control of n-i-n GaAs/AlGaAs-based resonant tunneling structures. Physical Review B. 2018; 98(7):075302. https://doi.org/10.1103/PhysRevB.98.075302</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation>Sawai S, Narahara K. Submillimeter-wave multiphase oscillation using traveling pulses in a resonant-tunneling diode-oscillator lattice. Journal of Infrared, Millimeter, and Terahertz Waves. 2021;42(4):426-445. https://doi.org/10.1007/s10762-021-00780-z</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation>Pchelintsev KP, Vetrova NA, Shashurin VD. Modeling of the degradation of resonant-tunneling diodes using artificial neural networks. Journal of Surface Investigation: X-ray, Synchrotron and Neutron Techniques. 2022;16(1): 82-85. https://doi.org/10.1134/S102745102201013X</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation>Vetrova NA, Pchelintsev KP, Shashurin VD. An artificial neural network as a predictor of electrical characteristics of nanoelectronic device channel based on a low-dimensional heterostructure. Journal of Physics: Conference Series. 2020;1695(1):012152. https://doi.org/10.1088/1742-6596/1695/1/012152</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation>Koehrsen W. Overfitting vs. underfitting: a complete example. Toronto: Towards Data Science; 2018.</mixed-citation></ref><ref id="B12"><label>12.</label><mixed-citation>Gavrilov AD, Jordache A, Vasdani M, Deng J. Preventing model overfitting and underfitting in convolutional neural networks. International Journal of Software Science and Computational Intelligence. 2018;10(4):19-28. https://doi.org/10.4018/IJSSCI.2018100102</mixed-citation></ref><ref id="B13"><label>13.</label><mixed-citation>Narayan S, Tagliarini G. An analysis of underfitting in MLP networks. 2005 IEEE International Joint Conference on Neural Networks. 2005;2:984-988. https://doi.org/10.1109/IJCNN.2005.1555986</mixed-citation></ref><ref id="B14"><label>14.</label><mixed-citation>Demuth HB, Beale MH, De Jess O, Hagan MT. Neural network design. Oklahoma: Martin Hagan; 2014.</mixed-citation></ref><ref id="B15"><label>15.</label><mixed-citation>Anantram MP, Lundstrom MS, Nikonov DE. Modeling of nanoscale devices. Proceedings of the IEEE. 2008; 96(9):1511-1550. https://doi.org/10.1109/JPROC.2008.927355</mixed-citation></ref><ref id="B16"><label>16.</label><mixed-citation>Datta S. Quantum transport: atom to transistor. Cambridge University Press; 2005.</mixed-citation></ref></ref-list></back></article>
