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/

Zendy Plus

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

Zendy Tools

Zendy Open

Deep learning is a powerful set of techniques for detecting complex patternsin data. However, when the causal structure of that process is underspecified,deep learning models can be brittle, lacking robustness to shifts in thedistribution of the data-generating process. In this paper, we turn to looppolarity analysis as a tool for specifying the causal structure of adata-generating process, in order to encode a more robust understanding of therelationship between system structure and system behavior within the deeplearning pipeline. We use simulated epidemic data based on an SIR model todemonstrate how measuring the polarity of the different feedback loops thatcompose a system can lead to more robust inferences on the part of neuralnetworks, improving the out-of-distribution performance of a deep learningmodel and infusing a system-dynamics-inspired approach into the machinelearning development pipeline.

Loop Polarity Analysis to Avoid Underspecification in Deep Learning