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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In real world scenarios, objects are often partially occluded. This requiresa robustness for object recognition against these perturbations. Convolutionalnetworks have shown good performances in classification tasks. The learnedconvolutional filters seem similar to receptive fields of simple cells found inthe primary visual cortex. Alternatively, spiking neural networks are morebiological plausible. We developed a two layer spiking network, trained onnatural scenes with a biologically plausible learning rule. It is compared totwo deep convolutional neural networks using a classification task of stepwisepixel erasement on MNIST. In comparison to these networks the spiking approachachieves good accuracy and robustness.

A Neural Spiking Approach Compared to Deep Feedforward Networks on Stepwise Pixel Erasement