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

Neuromorphic perception with event-based sensors, asynchronous hardware andspiking neurons is showing promising results for real-time and energy-efficientinference in embedded systems. The next promise of brain-inspired computing isto enable adaptation to changes at the edge with online learning. However, theparallel and distributed architectures of neuromorphic hardware based onco-localized compute and memory imposes locality constraints to the on-chiplearning rules. We propose in this work the Event-based Three-factor LocalPlasticity (ETLP) rule that uses (1) the pre-synaptic spike trace, (2) thepost-synaptic membrane voltage and (3) a third factor in the form of projectedlabels with no error calculation, that also serve as update triggers. We applyETLP with feedforward and recurrent spiking neural networks on visual andauditory event-based pattern recognition, and compare it to Back-PropagationThrough Time (BPTT) and eProp. We show a competitive performance in accuracywith a clear advantage in the computational complexity for ETLP. We also showthat when using local plasticity, threshold adaptation in spiking neurons and arecurrent topology are necessary to learn spatio-temporal patterns with a richtemporal structure. Finally, we provide a proof of concept hardwareimplementation of ETLP on FPGA to highlight the simplicity of its computationalprimitives and how they can be mapped into neuromorphic hardware for onlinelearning with low-energy consumption and real-time interaction.

ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware