English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Spiking neural networks (SNNs) serve as one type of efficient model toprocess spatio-temporal patterns in time series, such as the Address-EventRepresentation data collected from Dynamic Vision Sensor (DVS). Althoughconvolutional SNNs have achieved remarkable performance on these AER datasets,benefiting from the predominant spatial feature extraction ability ofconvolutional structure, they ignore temporal features related to sequentialtime points. In this paper, we develop a recurrent spiking neural network(RSNN) model embedded with an advanced spiking convolutional block attentionmodule (SCBAM) component to combine both spatial and temporal features ofspatio-temporal patterns. It invokes the history information in spatial andtemporal channels adaptively through SCBAM, which brings the advantages ofefficient memory calling and history redundancy elimination. The performance ofour model was evaluated in DVS128-Gesture dataset and other time-seriesdatasets. The experimental results show that the proposed SRNN-SCBAM modelmakes better use of the history information in spatial and temporal dimensionswith less memory space, and achieves higher accuracy compared to other models.

Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks