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

Deep neural networks are a key component of behavior prediction and motiongeneration for self-driving cars. One of their main drawbacks is a lack oftransparency: they should provide easy to interpret rationales for whattriggers certain behaviors. We propose an architecture called AttentionalBottleneck with the goal of improving transparency. Our key idea is to combinevisual attention, which identifies what aspects of the input the model isusing, with an information bottleneck that enables the model to only useaspects of the input which are important. This not only provides sparse andinterpretable attention maps (e.g. focusing only on specific vehicles in thescene), but it adds this transparency at no cost to model accuracy. In fact, wefind slight improvements in accuracy when applying Attentional Bottleneck tothe ChauffeurNet model, whereas we find that the accuracy deteriorates with atraditional visual attention model.

Attentional Bottleneck: Towards an Interpretable Deep Driving Network