Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network
The purpose of this study is to study the influence of synaptic plasticity on excitatory and inhibitory synapses on the formation of the feature space of the input image on the excitatory and inhibitory layers of neurons in a spiking neural network. Methods. To simulate the dynamics of the neuron,...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Saratov State University
2024-03-01
|
| Series: | Известия высших учебных заведений: Прикладная нелинейная динамика |
| Subjects: | |
| Online Access: | https://andjournal.sgu.ru/sites/andjournal.sgu.ru/files/text-pdf/2024/03/and_2024-2_lebedev-et-al_253-267.pdf |
| _version_ | 1797235619177431040 |
|---|---|
| author | Lebedev, Andrey Aleksandrovich Kazantsev, Viktor Borisovich Stasenko, Sergey Victorovich |
| author_facet | Lebedev, Andrey Aleksandrovich Kazantsev, Viktor Borisovich Stasenko, Sergey Victorovich |
| author_sort | Lebedev, Andrey Aleksandrovich |
| collection | DOAJ |
| description | The purpose of this study is to study the influence of synaptic plasticity on excitatory and inhibitory synapses on the formation of the feature space of the input image on the excitatory and inhibitory layers of neurons in a spiking neural network. Methods. To simulate the dynamics of the neuron, the computationally efficient model “Leaky integrate-and-fire” was used. The conductance-based synapse model was used as a synaptic contact model. Synaptic plasticity in excitatory and inhibitory synapses was modeled by the classical model of time dependent synaptic plasticity. A neural network composed of them generates a feature space, which is divided into classes by a machine learning algorithm. Results. A model of a spiking neural network was built with excitatory and inhibitory layers of neurons with adaptation of synaptic contacts due to synaptic plasticity. Various configurations of the model with synaptic plasticity were considered for the problem of forming the feature space of the input image on the excitatory and inhibitory layers of neurons, and their comparison was also carried out. Conclusion. It has been shown that synaptic plasticity in inhibitory synapses impairs the formation of an image feature space for a classification task. The model constraints are also obtained and the best model configuration is selected. |
| first_indexed | 2024-04-24T16:50:50Z |
| format | Article |
| id | doaj.art-9c36dacb983947ff8cb91ebcb595b1e4 |
| institution | Directory Open Access Journal |
| issn | 0869-6632 2542-1905 |
| language | English |
| last_indexed | 2024-04-24T16:50:50Z |
| publishDate | 2024-03-01 |
| publisher | Saratov State University |
| record_format | Article |
| series | Известия высших учебных заведений: Прикладная нелинейная динамика |
| spelling | doaj.art-9c36dacb983947ff8cb91ebcb595b1e42024-03-29T04:30:14ZengSaratov State UniversityИзвестия высших учебных заведений: Прикладная нелинейная динамика0869-66322542-19052024-03-0132225326710.18500/0869-6632-003092Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural networkLebedev, Andrey Aleksandrovich0Kazantsev, Viktor Borisovich1Stasenko, Sergey Victorovich2Lobachevsky State University of Nizhny Novgorod, 603950 Nizhny Novgorod, Gagarin Avenue, 23Institute of Applied Physics of the Russian Academy of Sciences, ul. Ul'yanova, 46, Nizhny Novgorod , 603950, RussiaLobachevsky State University of Nizhny Novgorod, 603950 Nizhny Novgorod, Gagarin Avenue, 23The purpose of this study is to study the influence of synaptic plasticity on excitatory and inhibitory synapses on the formation of the feature space of the input image on the excitatory and inhibitory layers of neurons in a spiking neural network. Methods. To simulate the dynamics of the neuron, the computationally efficient model “Leaky integrate-and-fire” was used. The conductance-based synapse model was used as a synaptic contact model. Synaptic plasticity in excitatory and inhibitory synapses was modeled by the classical model of time dependent synaptic plasticity. A neural network composed of them generates a feature space, which is divided into classes by a machine learning algorithm. Results. A model of a spiking neural network was built with excitatory and inhibitory layers of neurons with adaptation of synaptic contacts due to synaptic plasticity. Various configurations of the model with synaptic plasticity were considered for the problem of forming the feature space of the input image on the excitatory and inhibitory layers of neurons, and their comparison was also carried out. Conclusion. It has been shown that synaptic plasticity in inhibitory synapses impairs the formation of an image feature space for a classification task. The model constraints are also obtained and the best model configuration is selected.https://andjournal.sgu.ru/sites/andjournal.sgu.ru/files/text-pdf/2024/03/and_2024-2_lebedev-et-al_253-267.pdfspiking neural networksynaptic plasticitymachine learningimage classification |
| spellingShingle | Lebedev, Andrey Aleksandrovich Kazantsev, Viktor Borisovich Stasenko, Sergey Victorovich Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network Известия высших учебных заведений: Прикладная нелинейная динамика spiking neural network synaptic plasticity machine learning image classification |
| title | Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network |
| title_full | Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network |
| title_fullStr | Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network |
| title_full_unstemmed | Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network |
| title_short | Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network |
| title_sort | study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network |
| topic | spiking neural network synaptic plasticity machine learning image classification |
| url | https://andjournal.sgu.ru/sites/andjournal.sgu.ru/files/text-pdf/2024/03/and_2024-2_lebedev-et-al_253-267.pdf |
| work_keys_str_mv | AT lebedevandreyaleksandrovich studyoftheinfluenceofsynapticplasticityontheformationofafeaturespacebyaspikingneuralnetwork AT kazantsevviktorborisovich studyoftheinfluenceofsynapticplasticityontheformationofafeaturespacebyaspikingneuralnetwork AT stasenkosergeyvictorovich studyoftheinfluenceofsynapticplasticityontheformationofafeaturespacebyaspikingneuralnetwork |