Evaluation of the Effect of the Dynamic Behavior and Topology Co-Learning of Neurons and Synapses on the Small-Sample Learning Ability of Spiking Neural Network
Small sample learning ability is one of the most significant characteristics of the human brain. However, its mechanism is yet to be fully unveiled. In recent years, brain-inspired artificial intelligence has become a very hot research domain. Researchers explored brain-inspired technologies or arch...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3425/12/2/139 |
| _version_ | 1797482223736193024 |
|---|---|
| author | Xu Yang Yunlin Lei Mengxing Wang Jian Cai Miao Wang Ziyi Huan Xialv Lin |
| author_facet | Xu Yang Yunlin Lei Mengxing Wang Jian Cai Miao Wang Ziyi Huan Xialv Lin |
| author_sort | Xu Yang |
| collection | DOAJ |
| description | Small sample learning ability is one of the most significant characteristics of the human brain. However, its mechanism is yet to be fully unveiled. In recent years, brain-inspired artificial intelligence has become a very hot research domain. Researchers explored brain-inspired technologies or architectures to construct neural networks that could achieve human-alike intelligence. In this work, we presented our effort at evaluation of the effect of dynamic behavior and topology co-learning of neurons and synapses on the small sample learning ability of spiking neural network. Results show that the dynamic behavior and topology co-learning mechanism of neurons and synapses presented in our work could significantly reduce the number of required samples, while maintaining a reasonable performance on the MNIST data-set, resulting in a very lightweight neural network structure. |
| first_indexed | 2024-03-09T22:28:15Z |
| format | Article |
| id | doaj.art-b5a4063ef71b4e12b4129fa1425b8b26 |
| institution | Directory Open Access Journal |
| issn | 2076-3425 |
| language | English |
| last_indexed | 2024-03-09T22:28:15Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj.art-b5a4063ef71b4e12b4129fa1425b8b262023-11-23T19:02:11ZengMDPI AGBrain Sciences2076-34252022-01-0112213910.3390/brainsci12020139Evaluation of the Effect of the Dynamic Behavior and Topology Co-Learning of Neurons and Synapses on the Small-Sample Learning Ability of Spiking Neural NetworkXu Yang0Yunlin Lei1Mengxing Wang2Jian Cai3Miao Wang4Ziyi Huan5Xialv Lin6School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaSmall sample learning ability is one of the most significant characteristics of the human brain. However, its mechanism is yet to be fully unveiled. In recent years, brain-inspired artificial intelligence has become a very hot research domain. Researchers explored brain-inspired technologies or architectures to construct neural networks that could achieve human-alike intelligence. In this work, we presented our effort at evaluation of the effect of dynamic behavior and topology co-learning of neurons and synapses on the small sample learning ability of spiking neural network. Results show that the dynamic behavior and topology co-learning mechanism of neurons and synapses presented in our work could significantly reduce the number of required samples, while maintaining a reasonable performance on the MNIST data-set, resulting in a very lightweight neural network structure.https://www.mdpi.com/2076-3425/12/2/139small-sample learningspiking neural networkstructural learningadaptive structure |
| spellingShingle | Xu Yang Yunlin Lei Mengxing Wang Jian Cai Miao Wang Ziyi Huan Xialv Lin Evaluation of the Effect of the Dynamic Behavior and Topology Co-Learning of Neurons and Synapses on the Small-Sample Learning Ability of Spiking Neural Network Brain Sciences small-sample learning spiking neural network structural learning adaptive structure |
| title | Evaluation of the Effect of the Dynamic Behavior and Topology Co-Learning of Neurons and Synapses on the Small-Sample Learning Ability of Spiking Neural Network |
| title_full | Evaluation of the Effect of the Dynamic Behavior and Topology Co-Learning of Neurons and Synapses on the Small-Sample Learning Ability of Spiking Neural Network |
| title_fullStr | Evaluation of the Effect of the Dynamic Behavior and Topology Co-Learning of Neurons and Synapses on the Small-Sample Learning Ability of Spiking Neural Network |
| title_full_unstemmed | Evaluation of the Effect of the Dynamic Behavior and Topology Co-Learning of Neurons and Synapses on the Small-Sample Learning Ability of Spiking Neural Network |
| title_short | Evaluation of the Effect of the Dynamic Behavior and Topology Co-Learning of Neurons and Synapses on the Small-Sample Learning Ability of Spiking Neural Network |
| title_sort | evaluation of the effect of the dynamic behavior and topology co learning of neurons and synapses on the small sample learning ability of spiking neural network |
| topic | small-sample learning spiking neural network structural learning adaptive structure |
| url | https://www.mdpi.com/2076-3425/12/2/139 |
| work_keys_str_mv | AT xuyang evaluationoftheeffectofthedynamicbehaviorandtopologycolearningofneuronsandsynapsesonthesmallsamplelearningabilityofspikingneuralnetwork AT yunlinlei evaluationoftheeffectofthedynamicbehaviorandtopologycolearningofneuronsandsynapsesonthesmallsamplelearningabilityofspikingneuralnetwork AT mengxingwang evaluationoftheeffectofthedynamicbehaviorandtopologycolearningofneuronsandsynapsesonthesmallsamplelearningabilityofspikingneuralnetwork AT jiancai evaluationoftheeffectofthedynamicbehaviorandtopologycolearningofneuronsandsynapsesonthesmallsamplelearningabilityofspikingneuralnetwork AT miaowang evaluationoftheeffectofthedynamicbehaviorandtopologycolearningofneuronsandsynapsesonthesmallsamplelearningabilityofspikingneuralnetwork AT ziyihuan evaluationoftheeffectofthedynamicbehaviorandtopologycolearningofneuronsandsynapsesonthesmallsamplelearningabilityofspikingneuralnetwork AT xialvlin evaluationoftheeffectofthedynamicbehaviorandtopologycolearningofneuronsandsynapsesonthesmallsamplelearningabilityofspikingneuralnetwork |