Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier
One of the modern trends in the design of human−machine interfaces (HMI) is to involve the so called spiking neuron networks (SNNs) in signal processing. The SNNs can be trained by simple and efficient biologically inspired algorithms. In particular, we have shown that sensory neurons in t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/2/500 |
| _version_ | 1798038591713050624 |
|---|---|
| author | Sergey A. Lobov Andrey V. Chernyshov Nadia P. Krilova Maxim O. Shamshin Victor B. Kazantsev |
| author_facet | Sergey A. Lobov Andrey V. Chernyshov Nadia P. Krilova Maxim O. Shamshin Victor B. Kazantsev |
| author_sort | Sergey A. Lobov |
| collection | DOAJ |
| description | One of the modern trends in the design of human−machine interfaces (HMI) is to involve the so called spiking neuron networks (SNNs) in signal processing. The SNNs can be trained by simple and efficient biologically inspired algorithms. In particular, we have shown that sensory neurons in the input layer of SNNs can simultaneously encode the input signal based both on the spiking frequency rate and on varying the latency in generating spikes. In the case of such mixed temporal-rate coding, the SNN should implement learning working properly for both types of coding. Based on this, we investigate how a single neuron can be trained with pure rate and temporal patterns, and then build a universal SNN that is trained using mixed coding. In particular, we study Hebbian and competitive learning in SNN in the context of temporal and rate coding problems. We show that the use of Hebbian learning through pair-based and triplet-based spike timing-dependent plasticity (STDP) rule is accomplishable for temporal coding, but not for rate coding. Synaptic competition inducing depression of poorly used synapses is required to ensure a neural selectivity in the rate coding. This kind of competition can be implemented by the so-called forgetting function that is dependent on neuron activity. We show that coherent use of the triplet-based STDP and synaptic competition with the forgetting function is sufficient for the rate coding. Next, we propose a SNN capable of classifying electromyographical (EMG) patterns using an unsupervised learning procedure. The neuron competition achieved via lateral inhibition ensures the “winner takes all” principle among classifier neurons. The SNN also provides gradual output response dependent on muscular contraction strength. Furthermore, we modify the SNN to implement a supervised learning method based on stimulation of the target classifier neuron synchronously with the network input. In a problem of discrimination of three EMG patterns, the SNN with supervised learning shows median accuracy 99.5% that is close to the result demonstrated by multi-layer perceptron learned by back propagation of an error algorithm. |
| first_indexed | 2024-04-11T21:42:17Z |
| format | Article |
| id | doaj.art-a95a4e1dd52742bfb48a55e6780a27b6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:42:17Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a95a4e1dd52742bfb48a55e6780a27b62022-12-22T04:01:33ZengMDPI AGSensors1424-82202020-01-0120250010.3390/s20020500s20020500Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern ClassifierSergey A. Lobov0Andrey V. Chernyshov1Nadia P. Krilova2Maxim O. Shamshin3Victor B. Kazantsev4Neurotechnology Department, Lobachevsky State University of Nizhny Novgorod, 603950 Nizhny Novgorod, RussiaNeurotechnology Department, Lobachevsky State University of Nizhny Novgorod, 603950 Nizhny Novgorod, RussiaNeurotechnology Department, Lobachevsky State University of Nizhny Novgorod, 603950 Nizhny Novgorod, RussiaNeurotechnology Department, Lobachevsky State University of Nizhny Novgorod, 603950 Nizhny Novgorod, RussiaNeurotechnology Department, Lobachevsky State University of Nizhny Novgorod, 603950 Nizhny Novgorod, RussiaOne of the modern trends in the design of human−machine interfaces (HMI) is to involve the so called spiking neuron networks (SNNs) in signal processing. The SNNs can be trained by simple and efficient biologically inspired algorithms. In particular, we have shown that sensory neurons in the input layer of SNNs can simultaneously encode the input signal based both on the spiking frequency rate and on varying the latency in generating spikes. In the case of such mixed temporal-rate coding, the SNN should implement learning working properly for both types of coding. Based on this, we investigate how a single neuron can be trained with pure rate and temporal patterns, and then build a universal SNN that is trained using mixed coding. In particular, we study Hebbian and competitive learning in SNN in the context of temporal and rate coding problems. We show that the use of Hebbian learning through pair-based and triplet-based spike timing-dependent plasticity (STDP) rule is accomplishable for temporal coding, but not for rate coding. Synaptic competition inducing depression of poorly used synapses is required to ensure a neural selectivity in the rate coding. This kind of competition can be implemented by the so-called forgetting function that is dependent on neuron activity. We show that coherent use of the triplet-based STDP and synaptic competition with the forgetting function is sufficient for the rate coding. Next, we propose a SNN capable of classifying electromyographical (EMG) patterns using an unsupervised learning procedure. The neuron competition achieved via lateral inhibition ensures the “winner takes all” principle among classifier neurons. The SNN also provides gradual output response dependent on muscular contraction strength. Furthermore, we modify the SNN to implement a supervised learning method based on stimulation of the target classifier neuron synchronously with the network input. In a problem of discrimination of three EMG patterns, the SNN with supervised learning shows median accuracy 99.5% that is close to the result demonstrated by multi-layer perceptron learned by back propagation of an error algorithm.https://www.mdpi.com/1424-8220/20/2/500emg interfacestdppair-based stdptriplet-based stdptemporal codingrate codingsynaptic competitionneural competitionlateral inhibition |
| spellingShingle | Sergey A. Lobov Andrey V. Chernyshov Nadia P. Krilova Maxim O. Shamshin Victor B. Kazantsev Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier Sensors emg interface stdp pair-based stdp triplet-based stdp temporal coding rate coding synaptic competition neural competition lateral inhibition |
| title | Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier |
| title_full | Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier |
| title_fullStr | Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier |
| title_full_unstemmed | Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier |
| title_short | Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier |
| title_sort | competitive learning in a spiking neural network towards an intelligent pattern classifier |
| topic | emg interface stdp pair-based stdp triplet-based stdp temporal coding rate coding synaptic competition neural competition lateral inhibition |
| url | https://www.mdpi.com/1424-8220/20/2/500 |
| work_keys_str_mv | AT sergeyalobov competitivelearninginaspikingneuralnetworktowardsanintelligentpatternclassifier AT andreyvchernyshov competitivelearninginaspikingneuralnetworktowardsanintelligentpatternclassifier AT nadiapkrilova competitivelearninginaspikingneuralnetworktowardsanintelligentpatternclassifier AT maximoshamshin competitivelearninginaspikingneuralnetworktowardsanintelligentpatternclassifier AT victorbkazantsev competitivelearninginaspikingneuralnetworktowardsanintelligentpatternclassifier |