natszdravНациональное здравоохранениеNational Health Care (Russia)2713-069X2713-0703Federal State Autonomous Educational Institution of Higher Education I.M. Sechenov First Moscow State Medical University of the Ministry of Health of the Russian Federation (Sechenov University)10.47093/2713-069X.2023.4.1.31-39natszdrav-255Research ArticleПСИХИАТРИЯPSYCHIATRYМоделирование поведения человека в норме и при психической патологииModeling of human behavior in norm and mental pathologyhttps://orcid.org/0000-0003-4357-1105ДемидоваЛ. Ю.DemidovaL. Yu.

Демидова Любовь Юрьевна – канд. психол. наук, старший научный сотрудник отдела судебно-психиатрической экспертизы в уголовном процессе

Кропоткинский пер., д. 23, г. Москва, 119034

Liubov Yu. Demidova – Cand. of Sci. (Psychology), Senior Researcher, Department of Forensic Examination in Criminal Proceedings

Kropotkinsky Lane, 23, Moscow, 119034

https://orcid.org/0000-0002-7045-0547АхапкинР. В.AkhapkinR. V.

Ахапкин Роман Витальевич – д-р мед. наук, доцент, заместитель директора по научной работе Московского научно-исследовательского института психиатрии

Кропоткинский пер., д. 23, г. Москва, 119034

Roman V. Akhapkin – Dr. of Sci. (Medicine), Assistant Professor, Deputy Director for Research, Moscow Research Institute of Psychiatry

Kropotkinsky Lane, 23, Moscow, 119034

https://orcid.org/0000-0001-9922-3818ТкаченкоА. А.TkachenkoA. A.

Ткаченко Андрей Анатольевич – д-р мед. наук, профессор, руководитель отдела судебно-психиатрической экспертизы в уголовном процессе, профессор кафедры социальной и судебной психиатрии

 

Кропоткинский пер., д. 23, г. Москва, 119034

Andrey A. Tkachenko – Dr. of Sci. (Medicine), Professor, Head of the Department of Forensic Examination in Criminal Proceedings, Professor, Department of Social and Forensic Psychiatry

Kropotkinsky Lane, 23, Moscow, 119034

ФГБУ «Национальный медицинский исследовательский центр психиатрии и наркологии им. В.П. Сербского» Министерства здравоохранения Российской ФедерацииРоссияV. Serbsky National Medical Research Centre for Psychiatry and NarcologyRussian FederationФГБУ «Национальный медицинский исследовательский центр психиатрии и наркологии им. В.П. Сербского» Министерства здравоохранения Российской Федерации; ФГАОУ ВО «Первый Московский государственный медицинский университет им. И.М. Сеченова» Министерства здравоохранения Российской Федерации (Сеченовский Университет)РоссияV. Serbsky National Medical Research Centre for Psychiatry and Narcology; Sechenov First Moscow State Medical University (Sechenov University)Russian Federation202318052023413139Copyright © Демидова Л.Ю., Ахапкин Р.В., Ткаченко А.А., 20232023Демидова Л.Ю., Ахапкин Р.В., Ткаченко А.А.Demidova L.Y., Akhapkin R.V., Tkachenko A.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.natszdrav.ru/jour/article/view/255

Активное развитие научных технологий и цифровая трансформация здравоохранения обещают серьезный прорыв в понимании нормы и патологии, в оценке рисков возникновения заболеваний или особых психических состояний, в прогнозировании их течения и возможных последствий. Иными словами, возникают надежды, что в недалеком будущем наука позволит моделировать и предсказывать сложное поведение человека хотя бы в каких-то контекстах. В статье анализируется прогресс в области моделирования человеческого поведения в медицине и, в частности, в психиатрии, для которой объяснение поведенческих нарушений является наиболее актуальным. С целью анализа существующих способов моделирования поведения человека в норме и при психической патологии было просмотрено 1175 публикаций, из которых для дальнейшего изучения были отобраны 74 работы. В статье освещаются возможности моделирования человеческого поведения и его наиболее перспективные направления. Показаны ограниченные возможности такого моделирования в настоящее время. Большинство создаваемых моделей не проходят достаточной проверки и оказываются непригодны для решения реальных практических задач. Кроме того, наука далека от объяснения сложных вариантов человеческого поведения, под вопросом остается и сама возможность такого моделирования с помощью компьютерной архитектуры, которая существенно отличается от биологической. Рассмотрены варианты моделирования поведения, позволяющие решать конкретные практические задачи в психиатрии и в целом в здравоохранении и поэтому представляющиеся наиболее перспективными.

Active development of scientific technologies and the digital transformation of the healthcare service promise a serious breakthrough in understanding the norm and pathology, assessing the risks of diseases or specific mental conditions, predicting their course and possible consequences. In other words, there are hopes that in the nearest future science allows modeling and predicting of complex human behavior at least in some contexts. The article analyzes the progress in the field of human behavior modeling in medicine and, particularly, in psychiatry, for which the explanation of behavioral disorders is the most relevant. 1175 publications were reviewed and 74 of them were selected for further analysis of the exiting methods for human behavior modeling in norm and mental pathology. The article highlights the possibilities of human behavior modeling and its most promising prospects. The possibilities of such modeling at the present time are limited. Most part of the created models have no sufficient verification and are unsuitable for solving real practical problems. In addition, science progress is far from explaining complex variants of human behavior, and it is unclear if it is possible to model such behavior using computer architecture, which is significantly different from biological. Various behavioral models are considered, that allow to solve specific practical tasks in psychiatry and healthcare system, and therefore seem to be the most promising.

моделирование поведенияздравоохранениепсихиатрияискусственный интеллектпрогнозированиеmodeling of behaviorhealthcarepsychiatryartificial intelligencepredictionReferencesYampolskiy R.V. Behavioral modeling: an overview. American Journal of Applied Sciences. 2008; 5(5): 496–503.1 Yampolskiy R.V. Behavioral modeling: an overview. American Journal of Ap-plied Sciences. 2008; 5(5): 496–503.Brailsford S.C., Harper P.R., Pitt M. An analysis of the academic literature on simulation and modelling in health care. Journal of Simulation. 2009; 3(3): 130–140. https://doi.org/10.1057/jos2009102 Brailsford S.C., Harper P.R., Pitt M. An analysis of the academic literature on simulation and modelling in health care. Journal of Simulation. 2009; 3(3): 130–140. https://doi.org/10.1057/jos200910Silverman B.G., Hanrahan N., Huang L., et al. Artificial intelligence and human behavior modeling and simulation for mental health conditions. In: D.D Luxton (Ed.) Artificial intelligence in behavioral and mental health care. Academic Press. 2016, P. 163–183. https://doi.org/10.1016/B978-0-12-420248-1.00007-63 Silverman B.G., Hanrahan N., Huang L., Rabinowitz E.F., Lim S. Artificial intelligence and human behavior modeling and simulation for mental health conditions. In: D.D Luxton (Ed.) Artificial intelligence in behavioral and mental health care. Academic Press. 2016, P. 163–183. https://doi.org/10.1016/B978-0-12-420248-1.00007-6Baron G., Perrodeau E., Boutron I., Ravaud P. Reporting of analyses from randomized controlled trials with multiple arms: a systematic review. BMC Medicine. 2013; 11(1): 1–7. https://doi.org/10.1186/1741-7015-11-844 Baron G., Perrodeau E., Boutron I., Ravaud P. Reporting of analyses from randomized controlled trials with multiple arms: a systematic review. BMC Medicine. 2013; 11(1): 1–7. https://doi.org/10.1186/1741-7015-11-84Макушкина О.А., Березкин А.С., Дурнева М.Ю., Авдонина С.М. Апробация и внедрение методики структурированной оценки риска опасного поведения у лиц с психическими расстройствами. Социальная и клиническая психиатрия. 2017; 27(4): 18–23.5 Makushkina O.A., Berezkin A.S., Dourneva M.Yu., Avdonina S.M. Testing and the use of structured risk assessment of dangerous behaviours in mentally disordered persons. Social and Clinical Psychiatry. 2017; 27(4): 18–23 (In Russian).Сычев Д.А., Застрожин М.С., Смирнов В.В. и др. Ассоциация активности изофермента CYP2D6 с профилем эффективности и безопасности галоперидола у пациентов, страдающих патологическим влечением к алкоголю. Вестник Российского государственного медицинского университета. 2015; (4): 36–39.6 Sychev D.A., Zastrozhin M.S., Smirnov V.V., et al. Association between the activity of CYP2D6 enzyme and profile of efficacy and safety of haloperidol in patients with alcohol addiction. Bulletin of Russian State Medical University. 2015; (4): 36–39 (In Russian).Lydon-Staley D.M., Cornblath E.J., Blevins A.S., Bassett D.S. Modeling brain, symptom, and behavior in the winds of change. Neuropsychopharmacology. 2021; 46: 20–32. https://doi.org/10.1038/s41386-020-00805-67 Lydon-Staley D.M., Cornblath E.J., Blevins A.S., Bassett D.S. Modeling brain, symptom, and behavior in the winds of change. Neuropsychopharmacology. 2021; 46: 20–32. https://doi.org/10.1038/s41386-020-00805-6Baajour S.J., Chowdury A., Thomas P., et al. Disordered directional brain network interactions during learning dynamics in schizophrenia revealed by multivariate autoregressive models. Human Brain Mapping. 2020; 41(13): 3594–3607. https://doi.org/10.1002/HBM.250328 Baajour S.J., Chowdury A., Thomas P., et al. Disordered directional brain net-work interactions during learning dynamics in schizophrenia revealed by multivariate autoregressive models. Human Brain Mapping. 2020; 41(13): 3594–3607. https://doi.org/10.1002/HBM.25032Robinaugh D.J., Hoekstra R.H.A., Toner E.R., Borsboom D. The network approach to psychopathology: a review of the literature 2008–2018 and an agenda for future research. Psychological Medicine. 2020; 50(3): 353–366. https://doi.org/10.1017/S00332917190034049 Robinaugh D.J., Hoekstra R.H.A., Toner E.R., Borsboom D. The network approach to psychopathology: a review of the literature 2008–2018 and an agenda for future research. Psychological Medicine. 2020; 50(3): 353–366. https://doi.org/10.1017/S0033291719003404Sulis W. The Continuum between temperament and mental illness as dynamical phases and transitions. Frontiers in Psychiatry. 2020; 11: 614982. https://doi.org/10.3389/FPSYT.2020.61498210 Sulis W. The Continuum between temperament and mental illness as dynamical phases and transitions. Frontiers in Psychiatry. 2020; 11: 614982. https://doi.org/10.3389/FPSYT.2020.614982National Research Council. Toward precision medicine: building a knowledge network for biomedical research and a new taxonomy of disease. 2012. 142 p. https://doi.org/10.17226/1328411 National Research Council. Toward precision medicine: building a knowledge network for biomedical research and a new taxonomy of disease. 2012. 142 p. https://doi.org/10.17226/13284Williams L.M., Hack L.M. Precision psychiatry: using neuroscience insights to inform personally tailored, measurement-based care. American Psychiatric Association Publishing, 2021. 304 p.12 Williams L.M., Hack L.M. Precision psychiatry: using neuroscience insights to inform personally tailored, measurement-based care. American Psychiatric Association Publishing, 2021. 304 p.Leach I.M., van der Harst P., de Boer R.A. Pharmacoepigenetics in heart failure. Current heart failure reports. 2010; 7: 83–90. https://doi.org/10.1007/S11897-010-0011-Y13 Leach I.M., van der Harst P., de Boer R.A. Pharmacoepigenetics in heart failure. Current heart failure reports. 2010; 7: 83–90. https://doi.org/10.1007/S11897-010-0011-YNicholson J.K., Wilson I.D., Lindon J.C. Pharmacometabonomics as an effector for personalized medicine. Pharmacogenomics. 2011; 12(1): 103–111. https://doi.org/10.2217/PGS.10.15714 Nicholson J.K., Wilson I.D., Lindon J.C. Pharmacometabonomics as an effector for personalized medicine. Pharmacogenomics. 2011; 12(1): 103–111. https://doi.org/10.2217/PGS.10.157Andreev V.P. Pharmacoproteomics of obesity: definitions, role and a case study of dynamics of human plasma proteome. Pharmacogenomics. 2011; 12(1): 1363–1365. https://doi.org/10.2217/PGS.11.10115 Andreev V.P. Pharmacoproteomics of obesity: definitions, role and a case study of dynamics of human plasma proteome. Pharmacogenomics. 2011; 12(1): 1363–1365. https://doi.org/10.2217/PGS.11.101Fornito A., Bullmore E.T. Connectomic intermediate phenotypes for psychiatric disorders. Frontiers in psychiatry. 2012; 3: 32. https://doi.org/10.3389/FPSYT.2012.0003216 Fornito A., Bullmore E.T. Connectomic intermediate phenotypes for psychiatric disorders. Frontiers in psychiatry. 2012; 3: 32. https://doi.org/10.3389/FPSYT.2012.00032Rappaport S.M. Implications of the exposome for exposure science. Journal of exposure science and environmental epidemiology. 2011(1); 21: 5–9. https://doi.org/10.1038/JES.2010.5017 Rappaport S.M. Implications of the exposome for exposure science. Journal of exposure science and environmental epidemiology. 2011(1); 21: 5–9. https://doi.org/10.1038/JES.2010.50Bzdok D., Meyer-Lindenberg A. Machine learning for precision psychiatry: opportunities and challenges. Biological psychiatry. Cognitive neuroscience and neuroimaging. 2018; 3(3): 223–230. https://doi.org/10.1016/J.BPSC.2017.11.00718 Bzdok D., Meyer-Lindenberg A. Machine learning for precision psychiatry: opportunities and challenges. Biological psychiatry. Cognitive neuroscience and neuroimaging. 2018; 3(3): 223–230. https://doi.org/10.1016/J.BPSC.2017.11.007Nicoletti L., Padovano A., Vartuli F., Vetrano M. Human behavior modeling: a state of the art. In: Proceedings of the international defense and homeland security simulation workshop. 2016. P. 67–74. ISBN 978-88-97999-79-919 Nicoletti L., Padovano A., Vartuli F., Vetrano M. Human behavior modeling: a state of the art. In: Proceedings of the international defense and homeland security simulation workshop. 2016. P. 67–74. ISBN 978-88-97999-79-9Pradier M.F., Hughes M.C., McCoy T.H., et al. Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation. Neuropsychopharmacology. 2020; 46(2): 455–461. https://doi.org/10.1038/s41386-020-00838-x20 Pradier M.F., Hughes M.C., McCoy T.H., et al. Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation. Neuropsychopharmacology. 2020; 46(2): 455–461. https://doi.org/10.1038/s41386-020-00838-xZang C., Goodman M., Zhu Z., et al. Development of a screening algorithm for borderline personality disorder using electronic health records. Scientific Reports. 2022; 12: 11976. https://doi.org/10.1038/s41598-022-16160-z21 Zang C., Goodman M., Zhu Z., et al. Development of a screening algorithm for borderline personality disorder using electronic health records. Scientific Reports. 2022; 12: 11976. https://doi.org/10.1038/s41598-022-16160-zHochman E., Feldman B., Weizman A., et al. Development and validation of a machine learning-based postpartum depression prediction model: a nationwide cohort study. Depression and anxiety. 2021; 38(4): 400–411. https://doi.org/10.1002/DA.2312322 Hochman E., Feldman B., Weizman A., et al. Development and validation of a machine learning-based postpartum depression prediction model: a nationwide cohort study. Depression and anxiety. 2021; 38(4): 400–411. https://doi.org/10.1002/DA.23123Su C., Aseltine R., Doshi R., et al. Machine learning for suicide risk prediction in children and adolescents with electronic health records. Translational Psychiatry. 2020; 10: 413. https://doi.org/10.1038/s41398-020-01100-023 Su C., Aseltine R., Doshi R., et al. Machine learning for suicide risk prediction in children and adolescents with electronic health records. Translational Psychiatry. 2020; 10: 413. https://doi.org/10.1038/s41398-020-01100-0Marsch L.A. Digital health data-driven approaches to understand human behavior. Neuropsychopharmacology. 2020; 46: 191–196. https://doi.org/10.1038/s41386-020-0761-524 Marsch L.A. Digital health data-driven approaches to understand human behavior. Neuropsychopharmacology. 2020; 46: 191–196. https://doi.org/10.1038/s41386-020-0761-5Su C., Xu Z., Pathak J., Wang F. Deep learning in mental health outcome research: a scoping review. Translational Psychiatry. 2020; 10: 116. https://doi.org/10.1038/s41398-020-0780-325 Su C., Xu Z., Pathak J., Wang F. Deep learning in mental health outcome research: a scoping review. Translational Psychiatry. 2020; 10: 116. https://doi.org/10.1038/s41398-020-0780-3Ibrahim K., Noble S., He G., et al. Large-scale functional brain networks of maladaptive childhood aggression identified by connectome-based predictive modeling. Molecular Psychiatry. 2021; 27: 985–999. https://doi.org/10.1038/s41380-021-01317-526 Ibrahim K., Noble S., He G., et al. Large-scale functional brain networks of maladaptive childhood aggression identified by connectome-based predictive modeling. Molecular Psychiatry. 2021; 27: 985–999. https://doi.org/10.1038/s41380-021-01317-5Scheinost D., Dadashkarimi J., Finn E.S., et al. Functional connectivity during frustration: a preliminary study of predictive modeling of irritability in youth. Neuropsychopharmacology. 2021; 46: 1300–1306. https://doi.org/10.1038/s41386-020-00954-827 Scheinost D., Dadashkarimi J., Finn E.S., et al. Functional connectivity during frustration: a preliminary study of predictive modeling of irritability in youth. Neuropsychopharmacology. 2021; 46: 1300–1306. https://doi.org/10.1038/s41386-020-00954-8Beran T.N., Violato C. Structural equation modeling in medical research: a primer. BMC Research Notes. 2010; 3: 267. https://doi.org/10.1186/1756-0500-3-26728 Beran T.N., Violato C. Structural equation modeling in medical research: a primer. BMC Research Notes. 2010; 3: 267. https://doi.org/10.1186/1756-0500-3-267Ahmad N.F.H., Shuib L., Othman M.K. Knowledge based architecture for mental health care system. International Journal of Information System and Engineering. 2018; 6(2): 37–44.29 Ahmad N.F.H., Shuib L., Othman M.K. Knowledge based architecture for mental health care system. International Journal of Information System and Engineering. 2018; 6(2): 37–44.Kassim A.M., Zulkifli N.N., Rahim M.F., Keikhosrokiani P. Predicting the use of a knowledge-based system for collaborative surgical team. Journal of Physics: Conference Series. 2022; 2356: 012038. https://doi.org/10.1088/1742-6596/2356/1/01203830 Kassim A.M., Zulkifli N.N., Rahim M.F., Keikhosrokiani P. Predicting the use of a knowledge- based system for collaborative surgical team. Journal of Physics: Conference Series. 2022; 2356: 012038. https://doi.org/10.1088/1742-6596/2356/1/012038Rutherford S., Kia S.M., Wolfers T., et al. The normative modeling framework for computational psychiatry. Nature Protocols. 2022; 17: 1711–1734. https://doi.org/10.1038/s41596-022-00696-531 Rutherford S., Kia S.M., Wolfers T., et al. The normative modeling framework for computational psychiatry. Nature Protocols. 2022; 17: 1711–1734. https://doi.org/10.1038/s41596-022-00696-5Paranjape R., Sadanand A. Multi-agent systems for healthcare simulation and modeling: applications for system improvement. Hershey, PA: IGI Global, 2009. 304 p.32 Paranjape R., Sadanand A. Multi-agent systems for healthcare simulation and modeling: applications for system improvement. Hershey, PA: IGI Global, 2009. 304 p.Suomala J., Kauttonen J. Human’s intuitive mental models as a source of realistic artificial intelligence and engineering. Frontiers in Psychology. 2022; 13: 873289. https://doi.org/10.3389/FPSYG.2022.87328933 Suomala J., Kauttonen J. Human’s intuitive mental models as a source of realistic artificial intelligence and engineering. Frontiers in Psychology. 2022; 13: 873289. https://doi org/10.3389/FPSYG.2022.873289Горский А.С. Проблемы нейронауки с точки зрения теоретической физики. В кн.: Ушаков В.Л., Юдин Д.А. (Ред.) I национальный конгресс по когнитивным исследованиям, искусственному интеллекту и нейроинформатике. М.: Общероссийская общественная организация «Российская ассоциация искусственного интеллекта», 2020. С. 105–110.34 Gorsky A. Neuroscience problems through the eyes of theoretical physics. Key questions and few results. In: V.L. Ushakov, D.A. Yudin (Eds.) I National Congress on Cognitive Research, Artificial Intelligence and Neuroinformatics. M.: Russian public organization “Russian Association of Artificial Intelligence”, 2020. P. 105–110 (In Russian).Анохин К.В., Новоселов К.С., Смирнов С.К. и др. Искусственный интеллект для науки и наука для искусственного интеллекта. Вопросы философии. 2022; 3: 93–105. https://doi.org/10.21146/0042-8744-2022-3-93-10535 Anokhin K.V., Novoselov K.S., Smirnov S.K., et al. AI for science and science for AI. Russian Studies in Philosophy. 2022; (3): 93–105 (In Russian). https://doi.org/10.21146/0042-8744-2022-3-93-105Ткаченко А.А., Демидова Л.Ю. Построение общей модели саморегуляции в судебной психиатрии. Сообщение 4. Ситуация: воспоминание о будущем. Российский психиатрический журнал. 2020; 1: 27–41. https://doi.org/10.24411/1560-957X-2020-1200336 Tkachenko A.A., Demidova L.Yu. Development of the general model of self-regulation in forensic psychiatry. Paper 4. Situation: remembering of the future. Russian Journal of Psychiatry. 2020; 1: 27–41 (In Russian). https://doi.org/10.24411/1560-957X-2020-12003Ткаченко А.А., Демидова Л.Ю. Построение общей модели саморегуляции в судебной психиатрии. Сообщение 3. Рождение интенции. Российский психиатрический журнал. 2019; 2: 17–27. https://doi.org/10.24411/1560-957X-2019-1191637 Tkachenko A.A., Demidova L.Yu. Development of the general model of self-regulation in forensic psychiatry. Paper 3. Appearance of intention. Russian Journal of Psychiatry. 2019; 2: 17–27 (In Russian). https://doi.org/10.24411/1560-957X-2019-11916Gershman S.J., Horvitz E.J., Tenenbaum J.B. Computational rationality: a converging paradigm for intelligence in brains, minds, and machines. Science. 2015; 349(6245): 273–278. https://doi.org/10.1126/SCIENCE.AAC607638 Gershman S.J., Horvitz E.J., Tenenbaum J.B. Computational rationality: a converging paradigm for intelligence in brains, minds, and machines. Science. 2015; 349(6245): 273–278. https://doi.org/10.1126/SCIENCE.AAC6076Friston K., Moran R.J., Nagai Y., et al. World model learning and inference. Neural networks. 2021; 144: 573–590. https://doi.org/10.1016/J.NEUNET.2021.09.01139 Friston K., Moran R.J., Nagai Y., et al. World model learning and inference. Neural networks. 2021; 144: 573–590. https://doi.org/10.1016/J.NEUNET.2021.09.011Рассел С., Норвиг П. Искусственный интеллект: современный подход. М.: Издательский дом «Вильямс», 2006. 1408 с.40 Russel S., Norvig P. Artificial intelligence: a modern approach. Moscow: Williams Publishing House, 2006. 1408 p. (In Russian).Savage N. How AI and neuroscience drive each other forwards. Nature. 2019, 571(7766): S15–S17. https://doi.org/10.1038/D41586-019-02212-441 Savage N. How AI and neuroscience drive each other forwards. Nature. 2019, 571(7766): S15–S17. https://doi.org/10.1038/D41586-019-02212-4Laird J.E., Lebiere C., Rosenbloom P.S. A Standard Model for the Mind: Toward a Common Computational Framework Across Artificial Intelligence, Cognitive Science, Neuroscience, and Robotics. AI Magazine. 2017, 38(4): 13–26. https://doi.org/10.1609/aimag.v38i4.274442 Laird, J. E., Lebiere, C., Rosenbloom, P. S. A Standard Model for the Mind: Toward a Common Computational Framework Across Artificial Intelligence, Cognitive Science, Neuroscience, and Robotics. AI Magazine. 2017, 38(4): 13–26. https://doi.org/10.1609/aimag.v38i4.2744Bengio Y., Lecun Y., Hinton G. Deep learning for AI. Communications of the ACM. 2021; 64(7): 58–65. https://doi.org/10.1145/344825043 Bengio Y., Lecun Y., Hinton G. Deep learning for AI. Communications of the ACM. 2021; 64(7): 58–65. https://doi.org/10.1145/3448250

The authors declare that there are no conflicts of interest present.