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

Biologically inspired spiking neural networks (SNNs) are widely used torealize ultralow-power energy consumption. However, deep SNNs are not easy totrain due to the excessive firing of spiking neurons in the hidden layers. Totackle this problem, we propose a novel but simple normalization techniquecalled postsynaptic potential normalization. This normalization removes thesubtraction term from the standard normalization and uses the second raw momentinstead of the variance as the division term. The spike firing can becontrolled, enabling the training to proceed appropriating, by conducting thissimple normalization to the postsynaptic potential. The experimental resultsshow that SNNs with our normalization outperformed other models using othernormalizations. Furthermore, through the pre-activation residual blocks, theproposed model can train with more than 100 layers without other specialtechniques dedicated to SNNs.

Rethinking the role of normalization and residual blocks for spiking neural networks