Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916083929186304 |
|---|---|
| author | Xu, Qi Gao, Yuyuan Shen, Jiangrong Li, Yaxin Ran, Xuming Tang, Huajin Pan, Gang |
| author_facet | Xu, Qi Gao, Yuyuan Shen, Jiangrong Li, Yaxin Ran, Xuming Tang, Huajin Pan, Gang |
| contents | Spiking neural networks (SNNs) serve as one type of efficient model to process spatio-temporal patterns in time series, such as the Address-Event Representation data collected from Dynamic Vision Sensor (DVS). Although convolutional SNNs have achieved remarkable performance on these AER datasets, benefiting from the predominant spatial feature extraction ability of convolutional structure, they ignore temporal features related to sequential time points. In this paper, we develop a recurrent spiking neural network (RSNN) model embedded with an advanced spiking convolutional block attention module (SCBAM) component to combine both spatial and temporal features of spatio-temporal patterns. It invokes the history information in spatial and temporal channels adaptively through SCBAM, which brings the advantages of efficient memory calling and history redundancy elimination. The performance of our model was evaluated in DVS128-Gesture dataset and other time-series datasets. The experimental results show that the proposed SRNN-SCBAM model makes better use of the history information in spatial and temporal dimensions with less memory space, and achieves higher accuracy compared to other models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03719 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks Xu, Qi Gao, Yuyuan Shen, Jiangrong Li, Yaxin Ran, Xuming Tang, Huajin Pan, Gang Neural and Evolutionary Computing Spiking neural networks (SNNs) serve as one type of efficient model to process spatio-temporal patterns in time series, such as the Address-Event Representation data collected from Dynamic Vision Sensor (DVS). Although convolutional SNNs have achieved remarkable performance on these AER datasets, benefiting from the predominant spatial feature extraction ability of convolutional structure, they ignore temporal features related to sequential time points. In this paper, we develop a recurrent spiking neural network (RSNN) model embedded with an advanced spiking convolutional block attention module (SCBAM) component to combine both spatial and temporal features of spatio-temporal patterns. It invokes the history information in spatial and temporal channels adaptively through SCBAM, which brings the advantages of efficient memory calling and history redundancy elimination. The performance of our model was evaluated in DVS128-Gesture dataset and other time-series datasets. The experimental results show that the proposed SRNN-SCBAM model makes better use of the history information in spatial and temporal dimensions with less memory space, and achieves higher accuracy compared to other models. |
| title | Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2401.03719 |