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 human brain exhibits remarkable abilities in integrating temporallydistant sensory inputs for decision-making. However, existing brain-inspiredspiking neural networks (SNNs) have struggled to match their biologicalcounterpart in modeling long-term temporal relationships. To address thisproblem, this paper presents a novel Contextual Embedding LeakyIntegrate-and-Fire (CE-LIF) spiking neuron model. Specifically, the CE-LIFmodel incorporates a meticulously designed contextual embedding component intothe adaptive neuronal firing threshold, thereby enhancing the memory storage ofspiking neurons and facilitating effective sequential modeling. Additionally,theoretical analysis is provided to elucidate how the CE-LIF model enableslong-term temporal credit assignment. Remarkably, when compared tostate-of-the-art recurrent SNNs, feedforward SNNs comprising the proposedCE-LIF neurons demonstrate superior performance across extensive sequentialmodeling tasks in terms of classification accuracy, network convergence speed,and memory capacity.

Unleashing the Potential of Spiking Neural Networks for Sequential Modeling with Contextual Embedding