A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike
In recent years, neuroscientists have discovered that the neural information is encoded by spike trains with precise times. Supervised learning algorithm based on the precise times for spiking neurons becomes an important research field. Although many existing algorithms have the excellent learning...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9039652/ |
| _version_ | 1818875888622632960 |
|---|---|
| author | Guojun Chen Guoen Wang |
| author_facet | Guojun Chen Guoen Wang |
| author_sort | Guojun Chen |
| collection | DOAJ |
| description | In recent years, neuroscientists have discovered that the neural information is encoded by spike trains with precise times. Supervised learning algorithm based on the precise times for spiking neurons becomes an important research field. Although many existing algorithms have the excellent learning ability, most of their mechanisms still have some complex computations and certain limitations. Moreover, the discontinuity of spiking process also makes it very difficult to build an efficient algorithm. This paper proposes a supervised learning algorithm for spiking neurons using the kernel function of spike trains based on a unit of pair-spike. Firstly, we comprehensively divide the intervals of spike trains. Then, we construct an optimal selection and computation method of spikes based on the unit of pair-spike. This method avoids some wrong computations and reduces the computational cost by using each effective input spike only once in every epoch. Finally, we use the kernel function defined by an inner product operator to solve the computing problem of discontinue spike process and multiple output spikes. The proposed algorithm is successfully applied to many learning tasks of spike trains, where the effect of our optimal selection and computation method is verified and the influence of learning factors such as learning kernel, learning rate, and learning epoch is analyzed. Moreover, compared with other algorithms, all experimental results show that our proposed algorithm has the higher learning accuracy and good learning efficiency. |
| first_indexed | 2024-12-19T13:33:39Z |
| format | Article |
| id | doaj.art-8dcfc4d82b4a422097e406e5c89ca618 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T13:33:39Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8dcfc4d82b4a422097e406e5c89ca6182022-12-21T20:19:17ZengIEEEIEEE Access2169-35362020-01-018534275344210.1109/ACCESS.2020.29813469039652A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-SpikeGuojun Chen0https://orcid.org/0000-0002-1340-160XGuoen Wang1https://orcid.org/0000-0002-8315-7913School of Urban Design, Wuhan University, Wuhan, ChinaSchool of Urban Design, Wuhan University, Wuhan, ChinaIn recent years, neuroscientists have discovered that the neural information is encoded by spike trains with precise times. Supervised learning algorithm based on the precise times for spiking neurons becomes an important research field. Although many existing algorithms have the excellent learning ability, most of their mechanisms still have some complex computations and certain limitations. Moreover, the discontinuity of spiking process also makes it very difficult to build an efficient algorithm. This paper proposes a supervised learning algorithm for spiking neurons using the kernel function of spike trains based on a unit of pair-spike. Firstly, we comprehensively divide the intervals of spike trains. Then, we construct an optimal selection and computation method of spikes based on the unit of pair-spike. This method avoids some wrong computations and reduces the computational cost by using each effective input spike only once in every epoch. Finally, we use the kernel function defined by an inner product operator to solve the computing problem of discontinue spike process and multiple output spikes. The proposed algorithm is successfully applied to many learning tasks of spike trains, where the effect of our optimal selection and computation method is verified and the influence of learning factors such as learning kernel, learning rate, and learning epoch is analyzed. Moreover, compared with other algorithms, all experimental results show that our proposed algorithm has the higher learning accuracy and good learning efficiency.https://ieeexplore.ieee.org/document/9039652/Direct computationspike selectionspike train kernelspiking neural networksspiking neuronssupervised learning |
| spellingShingle | Guojun Chen Guoen Wang A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike IEEE Access Direct computation spike selection spike train kernel spiking neural networks spiking neurons supervised learning |
| title | A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike |
| title_full | A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike |
| title_fullStr | A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike |
| title_full_unstemmed | A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike |
| title_short | A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike |
| title_sort | supervised learning algorithm for spiking neurons using spike train kernel based on a unit of pair spike |
| topic | Direct computation spike selection spike train kernel spiking neural networks spiking neurons supervised learning |
| url | https://ieeexplore.ieee.org/document/9039652/ |
| work_keys_str_mv | AT guojunchen asupervisedlearningalgorithmforspikingneuronsusingspiketrainkernelbasedonaunitofpairspike AT guoenwang asupervisedlearningalgorithmforspikingneuronsusingspiketrainkernelbasedonaunitofpairspike AT guojunchen supervisedlearningalgorithmforspikingneuronsusingspiketrainkernelbasedonaunitofpairspike AT guoenwang supervisedlearningalgorithmforspikingneuronsusingspiketrainkernelbasedonaunitofpairspike |