Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks
Abstract The architecture design and multi-scale learning principles of the human brain that evolved over hundreds of millions of years are crucial to realizing human-like intelligence. Spiking neural network based Liquid State Machine (LSM) serves as a suitable architecture to study brain-inspired...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-43488-x |
| _version_ | 1827634901344583680 |
|---|---|
| author | Wenxuan Pan Feifei Zhao Yi Zeng Bing Han |
| author_facet | Wenxuan Pan Feifei Zhao Yi Zeng Bing Han |
| author_sort | Wenxuan Pan |
| collection | DOAJ |
| description | Abstract The architecture design and multi-scale learning principles of the human brain that evolved over hundreds of millions of years are crucial to realizing human-like intelligence. Spiking neural network based Liquid State Machine (LSM) serves as a suitable architecture to study brain-inspired intelligence because of its brain-inspired structure and the potential for integrating multiple biological principles. Existing researches on LSM focus on different certain perspectives, including high-dimensional encoding or optimization of the liquid layer, network architecture search, and application to hardware devices. There is still a lack of in-depth inspiration from the learning and structural evolution mechanism of the brain. Considering these limitations, this paper presents a novel LSM learning model that integrates adaptive structural evolution and multi-scale biological learning rules. For structural evolution, an adaptive evolvable LSM model is developed to optimize the neural architecture design of liquid layer with separation property. For brain-inspired learning of LSM, we propose a dopamine-modulated Bienenstock-Cooper-Munros (DA-BCM) method that incorporates global long-term dopamine regulation and local trace-based BCM synaptic plasticity. Comparative experimental results on different decision-making tasks show that introducing structural evolution of the liquid layer, and the DA-BCM regulation of the liquid layer and the readout layer could improve the decision-making ability of LSM and flexibly adapt to rule reversal. This work is committed to exploring how evolution can help to design more appropriate network architectures and how multi-scale neuroplasticity principles coordinated to enable the optimization and learning of LSMs for relatively complex decision-making tasks. |
| first_indexed | 2024-03-09T15:19:46Z |
| format | Article |
| id | doaj.art-a36bb93b3ebb4a8f9c1dfd6786d66e80 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:19:46Z |
| publishDate | 2023-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a36bb93b3ebb4a8f9c1dfd6786d66e802023-11-26T12:52:35ZengNature PortfolioScientific Reports2045-23222023-10-0113111310.1038/s41598-023-43488-xAdaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networksWenxuan Pan0Feifei Zhao1Yi Zeng2Bing Han3Brain-inspired Cognitive Intelligence Lab, Institute of Automation, Chinese Academy of SciencesBrain-inspired Cognitive Intelligence Lab, Institute of Automation, Chinese Academy of SciencesBrain-inspired Cognitive Intelligence Lab, Institute of Automation, Chinese Academy of SciencesBrain-inspired Cognitive Intelligence Lab, Institute of Automation, Chinese Academy of SciencesAbstract The architecture design and multi-scale learning principles of the human brain that evolved over hundreds of millions of years are crucial to realizing human-like intelligence. Spiking neural network based Liquid State Machine (LSM) serves as a suitable architecture to study brain-inspired intelligence because of its brain-inspired structure and the potential for integrating multiple biological principles. Existing researches on LSM focus on different certain perspectives, including high-dimensional encoding or optimization of the liquid layer, network architecture search, and application to hardware devices. There is still a lack of in-depth inspiration from the learning and structural evolution mechanism of the brain. Considering these limitations, this paper presents a novel LSM learning model that integrates adaptive structural evolution and multi-scale biological learning rules. For structural evolution, an adaptive evolvable LSM model is developed to optimize the neural architecture design of liquid layer with separation property. For brain-inspired learning of LSM, we propose a dopamine-modulated Bienenstock-Cooper-Munros (DA-BCM) method that incorporates global long-term dopamine regulation and local trace-based BCM synaptic plasticity. Comparative experimental results on different decision-making tasks show that introducing structural evolution of the liquid layer, and the DA-BCM regulation of the liquid layer and the readout layer could improve the decision-making ability of LSM and flexibly adapt to rule reversal. This work is committed to exploring how evolution can help to design more appropriate network architectures and how multi-scale neuroplasticity principles coordinated to enable the optimization and learning of LSMs for relatively complex decision-making tasks.https://doi.org/10.1038/s41598-023-43488-x |
| spellingShingle | Wenxuan Pan Feifei Zhao Yi Zeng Bing Han Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks Scientific Reports |
| title | Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks |
| title_full | Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks |
| title_fullStr | Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks |
| title_full_unstemmed | Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks |
| title_short | Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks |
| title_sort | adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks |
| url | https://doi.org/10.1038/s41598-023-43488-x |
| work_keys_str_mv | AT wenxuanpan adaptivestructureevolutionandbiologicallyplausiblesynapticplasticityforrecurrentspikingneuralnetworks AT feifeizhao adaptivestructureevolutionandbiologicallyplausiblesynapticplasticityforrecurrentspikingneuralnetworks AT yizeng adaptivestructureevolutionandbiologicallyplausiblesynapticplasticityforrecurrentspikingneuralnetworks AT binghan adaptivestructureevolutionandbiologicallyplausiblesynapticplasticityforrecurrentspikingneuralnetworks |