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 perception and control networks are likely to be a key componentof self-driving vehicles. These models need to be explainable - they shouldprovide easy-to-interpret rationales for their behavior - so that passengers,insurance companies, law enforcement, developers etc., can understand whattriggered a particular behavior. Here we explore the use of visualexplanations. These explanations take the form of real-time highlighted regionsof an image that causally influence the network's output (steering control).Our approach is two-stage. In the first stage, we use a visual attention modelto train a convolution network end-to-end from images to steering angle. Theattention model highlights image regions that potentially influence thenetwork's output. Some of these are true influences, but some are spurious. Wethen apply a causal filtering step to determine which input regions actuallyinfluence the output. This produces more succinct visual explanations and moreaccurately exposes the network's behavior. We demonstrate the effectiveness ofour model on three datasets totaling 16 hours of driving. We first show thattraining with attention does not degrade the performance of the end-to-endnetwork. Then we show that the network causally cues on a variety of featuresthat are used by humans while driving.

Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention