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

Convolutional neural networks are vulnerable to small $\ell^p$ adversarialattacks, while the human visual system is not. Inspired by neural networks inthe eye and the brain, we developed a novel artificial neural network modelthat recurrently collects data with a log-polar field of view that iscontrolled by attention. We demonstrate the effectiveness of this design as adefense against SPSA and PGD adversarial attacks. It also has beneficialproperties observed in the animal visual system, such as reflex-like pathwaysfor low-latency inference, fixed amount of computation independent of imagesize, and rotation and scale invariance. The code for experiments is availableat https://gitlab.com/exwzd-public/kiritani_ono_2020.

Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks