Biologically Inspired Spatial–Temporal Perceiving Strategies for Spiking Neural Network
A future unmanned system needs the ability to perceive, decide and control in an open dynamic environment. In order to fulfill this requirement, it needs to construct a method with a universal environmental perception ability. Moreover, this perceptual process needs to be interpretable and understan...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/1/48 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589010688540672 |
|---|---|
| author | Yu Zheng Jingfeng Xue Jing Liu Yanjun Zhang |
| author_facet | Yu Zheng Jingfeng Xue Jing Liu Yanjun Zhang |
| author_sort | Yu Zheng |
| collection | DOAJ |
| description | A future unmanned system needs the ability to perceive, decide and control in an open dynamic environment. In order to fulfill this requirement, it needs to construct a method with a universal environmental perception ability. Moreover, this perceptual process needs to be interpretable and understandable, so that future interactions between unmanned systems and humans can be unimpeded. However, current mainstream DNN (deep learning neural network)-based AI (artificial intelligence) is a ‘black box’. We cannot interpret or understand how the decision is made by these AIs. An SNN (spiking neural network), which is more similar to a biological brain than a DNN, has the potential to implement interpretable or understandable AI. In this work, we propose a neuron group-based structural learning method for an SNN to better capture the spatial and temporal information from the external environment, and propose a time-slicing scheme to better interpret the spatial and temporal information of responses generated by an SNN. Results show that our method indeed helps to enhance the environment perception ability of the SNN, and possesses a certain degree of robustness, enhancing the potential to build an interpretable or understandable AI in the future. |
| format | Article |
| id | doaj-art-d2e83aee821b49b6bd2a8d849750125a |
| institution | Kabale University |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-d2e83aee821b49b6bd2a8d849750125a2025-01-24T13:24:43ZengMDPI AGBiomimetics2313-76732025-01-011014810.3390/biomimetics10010048Biologically Inspired Spatial–Temporal Perceiving Strategies for Spiking Neural NetworkYu Zheng0Jingfeng Xue1Jing Liu2Yanjun Zhang3Beijing Institute of Technology, Beijing 100081, ChinaBeijing Institute of Technology, Beijing 100081, ChinaBeijing Institute of Technology, Beijing 100081, ChinaBeijing Institute of Technology, Beijing 100081, ChinaA future unmanned system needs the ability to perceive, decide and control in an open dynamic environment. In order to fulfill this requirement, it needs to construct a method with a universal environmental perception ability. Moreover, this perceptual process needs to be interpretable and understandable, so that future interactions between unmanned systems and humans can be unimpeded. However, current mainstream DNN (deep learning neural network)-based AI (artificial intelligence) is a ‘black box’. We cannot interpret or understand how the decision is made by these AIs. An SNN (spiking neural network), which is more similar to a biological brain than a DNN, has the potential to implement interpretable or understandable AI. In this work, we propose a neuron group-based structural learning method for an SNN to better capture the spatial and temporal information from the external environment, and propose a time-slicing scheme to better interpret the spatial and temporal information of responses generated by an SNN. Results show that our method indeed helps to enhance the environment perception ability of the SNN, and possesses a certain degree of robustness, enhancing the potential to build an interpretable or understandable AI in the future.https://www.mdpi.com/2313-7673/10/1/48brain inspiredspiking neural networkneuron pairstime slicingenvironment perception |
| spellingShingle | Yu Zheng Jingfeng Xue Jing Liu Yanjun Zhang Biologically Inspired Spatial–Temporal Perceiving Strategies for Spiking Neural Network Biomimetics brain inspired spiking neural network neuron pairs time slicing environment perception |
| title | Biologically Inspired Spatial–Temporal Perceiving Strategies for Spiking Neural Network |
| title_full | Biologically Inspired Spatial–Temporal Perceiving Strategies for Spiking Neural Network |
| title_fullStr | Biologically Inspired Spatial–Temporal Perceiving Strategies for Spiking Neural Network |
| title_full_unstemmed | Biologically Inspired Spatial–Temporal Perceiving Strategies for Spiking Neural Network |
| title_short | Biologically Inspired Spatial–Temporal Perceiving Strategies for Spiking Neural Network |
| title_sort | biologically inspired spatial temporal perceiving strategies for spiking neural network |
| topic | brain inspired spiking neural network neuron pairs time slicing environment perception |
| url | https://www.mdpi.com/2313-7673/10/1/48 |
| work_keys_str_mv | AT yuzheng biologicallyinspiredspatialtemporalperceivingstrategiesforspikingneuralnetwork AT jingfengxue biologicallyinspiredspatialtemporalperceivingstrategiesforspikingneuralnetwork AT jingliu biologicallyinspiredspatialtemporalperceivingstrategiesforspikingneuralnetwork AT yanjunzhang biologicallyinspiredspatialtemporalperceivingstrategiesforspikingneuralnetwork |