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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deemed as the third generation of neural networks, the event-driven SpikingNeural Networks(SNNs) combined with bio-plausible local learning rules make itpromising to build low-power, neuromorphic hardware for SNNs. However, becauseof the non-linearity and discrete property of spiking neural networks, thetraining of SNN remains difficult and is still under discussion. Originatingfrom gradient descent, backprop has achieved stunning success in multi-layerSNNs. Nevertheless, it is assumed to lack biological plausibility, whileconsuming relatively high computational resources. In this paper, we propose anovel learning algorithm inspired by predictive coding theory and show that itcan perform supervised learning fully autonomously and successfully as thebackprop, utilizing only local Hebbian plasticity. Furthermore, this methodachieves a favorable performance compared to the state-of-the-art multi-layerSNNs: test accuracy of 99.25% for the Caltech Face/Motorbike dataset, 84.25%for the ETH-80 dataset, 98.1% for the MNIST dataset and 98.5% for theneuromorphic dataset: N-MNIST. Furthermore, our work provides a new perspectiveon how supervised learning algorithms are directly implemented in spikingneural circuitry, which may give some new insights into neuromorphologicalcalculation in neuroscience.

PC-SNN: Supervised Learning with Local Hebbian Synaptic Plasticity based on Predictive Coding in Spiking Neural Networks