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

Deep neural networks have surpassed human performance in key visualchallenges such as object recognition, but require a large amount of energy,computation, and memory. In contrast, spiking neural networks (SNNs) have thepotential to improve both the efficiency and biological plausibility of objectrecognition systems. Here we present a SNN model that uses spike-latency codingand winner-take-all inhibition (WTA-I) to efficiently represent visual stimulifrom the Fashion MNIST dataset. Stimuli were preprocessed with center-surroundreceptive fields and then fed to a layer of spiking neurons whose synapticweights were updated using spike-timing-dependent-plasticity (STDP). Weinvestigate how the quality of the represented objects changes under differentWTA-I schemes and demonstrate that a network of 150 spiking neurons canefficiently represent objects with as little as 40 spikes. Studying how coreobject recognition may be implemented using biologically plausible learningrules in SNNs may not only further our understanding of the brain, but alsolead to novel and efficient artificial vision systems.

Efficient visual object representation using a biologically plausible spike-latency code and winner-take-all inhibition