Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923243
Valentina Y. Guleva
Systems of intelligent interacting agents demonstrate high complexity of learning process due to complexity of single agent learning combined with their communication. Agent interactions are aimed at enhancing speed, quality, and complexity characterictics, nevetheless, each interaction may worse single agent results as well as enhance them. Therefore, building effective communication patterns is of high interest for learning process of intelligent systems. As an applied task, we consider project execution dynamics, where single tasks are assigned to employees having several conflicting parameters, while an intelligent system consists of multiple intelligent agents, learned by reinforcement algorithms. Different patterns of interaction according to agent similarities are explored as a factor affecting learning process. The condition of two agents connection is there similarity value, greater than some determined threshold; similarity function is determined for five static and dynamics parameters, and their influence is regulated by the corresponding five multipliers. The experiment shows there are significant parameters, showing more effect of connection on learning dynamics. This can be seen via effect of parameters, regulating neighbours contribution.
{"title":"Node Correlation Effects on Learning Dynamics in Networked Multiagent Reinforcement Learning","authors":"Valentina Y. Guleva","doi":"10.1109/DCNA56428.2022.9923243","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923243","url":null,"abstract":"Systems of intelligent interacting agents demonstrate high complexity of learning process due to complexity of single agent learning combined with their communication. Agent interactions are aimed at enhancing speed, quality, and complexity characterictics, nevetheless, each interaction may worse single agent results as well as enhance them. Therefore, building effective communication patterns is of high interest for learning process of intelligent systems. As an applied task, we consider project execution dynamics, where single tasks are assigned to employees having several conflicting parameters, while an intelligent system consists of multiple intelligent agents, learned by reinforcement algorithms. Different patterns of interaction according to agent similarities are explored as a factor affecting learning process. The condition of two agents connection is there similarity value, greater than some determined threshold; similarity function is determined for five static and dynamics parameters, and their influence is regulated by the corresponding five multipliers. The experiment shows there are significant parameters, showing more effect of connection on learning dynamics. This can be seen via effect of parameters, regulating neighbours contribution.","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122374581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923224
Illarion Ushakov, M. Mishchenko, V. Matrosov
The phenomenon of self-organized criticality in a neural network with the “Small-world” topology has been studied. We studied the critical value of coupling strength as a function of the total number of connections in the network. The dependence of critical coupling strength on the number of connections obeys the power law.
{"title":"Self-organized criticality in a neural network with the small-world topology","authors":"Illarion Ushakov, M. Mishchenko, V. Matrosov","doi":"10.1109/DCNA56428.2022.9923224","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923224","url":null,"abstract":"The phenomenon of self-organized criticality in a neural network with the “Small-world” topology has been studied. We studied the critical value of coupling strength as a function of the total number of connections in the network. The dependence of critical coupling strength on the number of connections obeys the power law.","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127908763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923218
D. M. Semenov, S. Plotnikov, Alexander L. Fradkov
The paper studies controlled synchronization in regular delay-coupled Hindmarsh-Rose network with a constant delay. It is the fact that signal propagation delays between nodes can hinder their synchronization. This investigation introduces a controller that can ensure the asymptotic synchronization between neurons in the network under study. The provided analysis is based on the Lyapunov-Krasovskii method.
{"title":"Controlled synchronization in regular delay-coupled networks of Hindmarsh-Rose neurons","authors":"D. M. Semenov, S. Plotnikov, Alexander L. Fradkov","doi":"10.1109/DCNA56428.2022.9923218","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923218","url":null,"abstract":"The paper studies controlled synchronization in regular delay-coupled Hindmarsh-Rose network with a constant delay. It is the fact that signal propagation delays between nodes can hinder their synchronization. This investigation introduces a controller that can ensure the asymptotic synchronization between neurons in the network under study. The provided analysis is based on the Lyapunov-Krasovskii method.","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129340504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923176
N. Stankevich, Elmira Bagautdinova
A family of Hodgkin-Huxley-type models demonstrating bistability between silent state and bursting oscillations is proposed. In models several ion channels were taking into account to achieve some specific types of bistability and behavior. We studied parameter space of our models with method of chart of dynamical regimes, areas of bistability were localized. Scenarios of bistability occurrence is described. Specific time series character for new ion channel are studied
{"title":"The simplest neuron models with bistability occurring as a result of accounting new ion channels","authors":"N. Stankevich, Elmira Bagautdinova","doi":"10.1109/DCNA56428.2022.9923176","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923176","url":null,"abstract":"A family of Hodgkin-Huxley-type models demonstrating bistability between silent state and bursting oscillations is proposed. In models several ion channels were taking into account to achieve some specific types of bistability and behavior. We studied parameter space of our models with method of chart of dynamical regimes, areas of bistability were localized. Scenarios of bistability occurrence is described. Specific time series character for new ion channel are studied","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130671827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923133
M. Mishchenko, Natalia S. Kovaleva, D. Bolshakov, V. Matrosov
Complex networks describe a wide range of systems in nature and society. Every complex network has certain topological features which strongly influence the dynamics. We studied the dynamics of a complex network of excitable elements with different coupling topologies. The role of network topology, noise level and coupling strength on the resulting dynamical modes has been observed. The effect of hub removal on network dynamics has been studied.
{"title":"The role of connections topology on synchronization in neural network","authors":"M. Mishchenko, Natalia S. Kovaleva, D. Bolshakov, V. Matrosov","doi":"10.1109/DCNA56428.2022.9923133","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923133","url":null,"abstract":"Complex networks describe a wide range of systems in nature and society. Every complex network has certain topological features which strongly influence the dynamics. We studied the dynamics of a complex network of excitable elements with different coupling topologies. The role of network topology, noise level and coupling strength on the resulting dynamical modes has been observed. The effect of hub removal on network dynamics has been studied.","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127837517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923314
D. Vlasov, R. Rybka, A. Sboev, A. Serenko, A. Minnekhanov, V. A. Demin
The reinforcement learning paradigm is for the first time presented for spiking neural network architecture with memristor-based local dynamic plasticity. The models of two kinds of such plasticity are used in the simulation study of the Cartpole task. Applying the Gaussian receptive field time-encoding scheme and simple reinforcing current pulses determined by the sign of reward change, the successful learning is demonstrated for both types of memristive plasticity.
{"title":"Reinforcement learning in a spiking neural network with memristive plasticity","authors":"D. Vlasov, R. Rybka, A. Sboev, A. Serenko, A. Minnekhanov, V. A. Demin","doi":"10.1109/DCNA56428.2022.9923314","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923314","url":null,"abstract":"The reinforcement learning paradigm is for the first time presented for spiking neural network architecture with memristor-based local dynamic plasticity. The models of two kinds of such plasticity are used in the simulation study of the Cartpole task. Applying the Gaussian receptive field time-encoding scheme and simple reinforcing current pulses determined by the sign of reward change, the successful learning is demonstrated for both types of memristive plasticity.","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128931357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923180
Mortin Konstantin, Shamshin Maksim
The paper presents a mathematical model of a fuzzy subset of a defect in a digital image and is described as a piecewise constant function. The analysis of the filtering of the flaw detection image is given to ensure the implementation of the quantization algorithm of detection with subsequent adaptive binarization of the obtained result. The developed method makes it possible to detect a sheet metal defect of the longitudinal crack type and calculate various geometric parameters of this defect. This approach allows not only to see the detection of a longitudinal crack, but also to minimize the errors of the second level of false positives on flaw detection images. The above result is compared with the annotation of the flaw detector and with the YOLOv3 neural network.
{"title":"Development of methods and algorithms of technical vision for detecting the defect longitudinal crack on sheet metal","authors":"Mortin Konstantin, Shamshin Maksim","doi":"10.1109/DCNA56428.2022.9923180","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923180","url":null,"abstract":"The paper presents a mathematical model of a fuzzy subset of a defect in a digital image and is described as a piecewise constant function. The analysis of the filtering of the flaw detection image is given to ensure the implementation of the quantization algorithm of detection with subsequent adaptive binarization of the obtained result. The developed method makes it possible to detect a sheet metal defect of the longitudinal crack type and calculate various geometric parameters of this defect. This approach allows not only to see the detection of a longitudinal crack, but also to minimize the errors of the second level of false positives on flaw detection images. The above result is compared with the annotation of the flaw detector and with the YOLOv3 neural network.","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129062693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923082
A. Petukhov, A. Polevaia, S. Polevaya
The purpose of the presented study is to assess the cognitive potential of a person based on the experimental data obtained in order to identify the cognitive capabilities of a person and its dynamics, e.g., to monitor recovery after a disease. To assess cognitive potential, two algorithms have been developed, one for assessing the level of cognitive complexity of a task, and the other for assessing the level of cognitive potential in a person. A complex of experimental methods has been applied using specially developed authorial methods; to assess the cognitive potential in an individual, mathematical methods for data processing and calculation of the introduced specific parameters were used. Specific methods are proposed using author's mathematical formulas for assessing the cognitive potential of a person based on experimental data and tasks of varying cognitive complexity as stimuli. Within the framework of this study, the methodology for assessing the value of cognitive potential in people based on the information representations (images) theory was created. To assess cognitive skills, including the so-called soft skills, a special online solution with the set of tools has been developed. The obtained parameters allow us to study the effect of social, genetic, and pathogenetic factors on cognitive potential. A theoretical approach and a technological platform for digital mapping of cognitive potential are proposed.
{"title":"Measuring Cognitive Potential in People while Performing Tasks with Varying Complexity","authors":"A. Petukhov, A. Polevaia, S. Polevaya","doi":"10.1109/DCNA56428.2022.9923082","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923082","url":null,"abstract":"The purpose of the presented study is to assess the cognitive potential of a person based on the experimental data obtained in order to identify the cognitive capabilities of a person and its dynamics, e.g., to monitor recovery after a disease. To assess cognitive potential, two algorithms have been developed, one for assessing the level of cognitive complexity of a task, and the other for assessing the level of cognitive potential in a person. A complex of experimental methods has been applied using specially developed authorial methods; to assess the cognitive potential in an individual, mathematical methods for data processing and calculation of the introduced specific parameters were used. Specific methods are proposed using author's mathematical formulas for assessing the cognitive potential of a person based on experimental data and tasks of varying cognitive complexity as stimuli. Within the framework of this study, the methodology for assessing the value of cognitive potential in people based on the information representations (images) theory was created. To assess cognitive skills, including the so-called soft skills, a special online solution with the set of tools has been developed. The obtained parameters allow us to study the effect of social, genetic, and pathogenetic factors on cognitive potential. A theoretical approach and a technological platform for digital mapping of cognitive potential are proposed.","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115865483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923177
Vadim Grubov, Sergey Afinogenov, V. Maximenko, N. Utyashev
In the present study we implemented machine learning approach to detect seizures on epileptic EEG data. We aimed to propose a method for preliminary EEG marking, that can possibly find application in clinical decision support system.
{"title":"Epileptic EEG marking with machine learning approach","authors":"Vadim Grubov, Sergey Afinogenov, V. Maximenko, N. Utyashev","doi":"10.1109/DCNA56428.2022.9923177","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923177","url":null,"abstract":"In the present study we implemented machine learning approach to detect seizures on epileptic EEG data. We aimed to propose a method for preliminary EEG marking, that can possibly find application in clinical decision support system.","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117003144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-14DOI: 10.1109/DCNA56428.2022.9923199
N. Babbysh
Classical models of artificial neural networks have several disadvantages. To eliminate these shortcomings, a fundamentally new model of an artificial neural network, called the interferential model, is proposed. This model is based on the structure of biological neurons of the human brain. This work describes principles of work of interferential model. The results of the work show that the interferential model does not contain the disadvantages of classical neural networks. It is well suited for running classification task, as well as for pattern recognition.
{"title":"Data classification using interferential neural network model","authors":"N. Babbysh","doi":"10.1109/DCNA56428.2022.9923199","DOIUrl":"https://doi.org/10.1109/DCNA56428.2022.9923199","url":null,"abstract":"Classical models of artificial neural networks have several disadvantages. To eliminate these shortcomings, a fundamentally new model of an artificial neural network, called the interferential model, is proposed. This model is based on the structure of biological neurons of the human brain. This work describes principles of work of interferential model. The results of the work show that the interferential model does not contain the disadvantages of classical neural networks. It is well suited for running classification task, as well as for pattern recognition.","PeriodicalId":110836,"journal":{"name":"2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125240057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：