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

Science meets Engineering in Deep Learning took place in Vancouver as part ofthe Workshop section of NeurIPS 2019. As organizers of the workshop, we createdthe following report in an attempt to isolate emerging topics and recurringthemes that have been presented throughout the event. Deep learning can stillbe a complex mix of art and engineering despite its tremendous success inrecent years. The workshop aimed at gathering people across the board toaddress seemingly contrasting challenges in the problems they are working on.As part of the call for the workshop, particular attention has been given tothe interdependence of architecture, data, and optimization that gives rise toan enormous landscape of design and performance intricacies that are notwell-understood. This year, our goal was to emphasize the following directionsin our community: (i) identify obstacles in the way to better models andalgorithms; (ii) identify the general trends from which we would like to buildscientific and potentially theoretical understanding; and (iii) the rigorousdesign of scientific experiments and experimental protocols whose purpose is toresolve and pinpoint the origin of mysteries while ensuring reproducibility androbustness of conclusions. In the event, these topics emerged and were broadlydiscussed, matching our expectations and paving the way for new studies inthese directions. While we acknowledge that the text is naturally biased as itcomes through our lens, here we present an attempt to do a fair job ofhighlighting the outcome of the workshop.

Post-Workshop Report on Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver