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

The identification of sensory cues associated with potential opportunitiesand dangers is frequently complicated by unrelated events that separate usefulcues by long delays. As a result, it remains a challenging task forstate-of-the-art spiking neural networks (SNNs) to establish long-term temporaldependency between distant cues. To address this challenge, we propose a novelbiologically inspired Two-Compartment Leaky Integrate-and-Fire spiking neuronmodel, dubbed TC-LIF. The proposed model incorporates carefully designedsomatic and dendritic compartments that are tailored to facilitate learninglong-term temporal dependencies. Furthermore, a theoretical analysis isprovided to validate the effectiveness of TC-LIF in propagating error gradientsover an extended temporal duration. Our experimental results, on a diverserange of temporal classification tasks, demonstrate superior temporalclassification capability, rapid training convergence, and high energyefficiency of the proposed TC-LIF model. Therefore, this work opens up a myriadof opportunities for solving challenging temporal processing tasks on emergingneuromorphic computing systems. Our code is publicly available athttps://github.com/ZhangShimin1/TC-LIF.

TC-LIF: A Two-Compartment Spiking Neuron Model for Long-term Sequential Modelling