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

We consider how human-centered causal theories and tools from the dynamicalsystems literature can be deployed to guide the representation of data whentraining neural networks for complex classification tasks. Specifically, we usesimulated data to show that training a neural network with a datarepresentation that makes explicit the invariant structural causal features ofthe data generating process of an epidemic system improves out-of-distribution(OOD) generalization performance on a classification task as compared to a morenaive approach to data representation. We take these results to demonstratethat using human-generated causal knowledge to reduce the epistemic uncertaintyof ML developers can lead to more well-specified ML pipelines. This, in turn,points to the utility of a dynamical systems approach to the broader effortaimed at improving the robustness and safety of machine learning systems viaimproved ML system development practices.

Causal Theories and Structural Data Representations for Improving Out-of-Distribution Classification