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

We present new theoretical foundations for unsupervisedSpike-Timing-Dependent Plasticity (STDP) learning in spiking neural networks(SNNs). In contrast to empirical parameter search used in most previous works,we provide novel theoretical grounds for SNN and STDP parameter tuning whichconsiderably reduces design time. Using our generic framework, we propose aclass of global, action-based and convolutional SNN-STDP architectures forlearning spatio-temporal features from event-based cameras. We assess ourmethods on the N-MNIST, the CIFAR10-DVS and the IBM DVS128 Gesture datasets,all acquired with a real-world event camera. Using our framework, we reportsignificant improvements in classification accuracy compared to bothconventional state-of-the-art event-based feature descriptors (+8.2% onCIFAR10-DVS), and compared to state-of-the-art STDP-based systems (+9.3% onN-MNIST, +7.74% on IBM DVS128 Gesture). Our work contributes to bothultra-low-power learning in neuromorphic edge devices, and towards abiologically-plausible, optimization-based theory of cortical vision.

A New Look at Spike-Timing-Dependent Plasticity Networks for Spatio-Temporal Feature Learning