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

This paper introduces a first implementation of a novellikelihood-ratio-based approach for constructing confidence intervals forneural networks. Our method, called DeepLR, offers several qualitativeadvantages: most notably, the ability to construct asymmetric intervals thatexpand in regions with a limited amount of data, and the inherent incorporationof factors such as the amount of training time, network architecture, andregularization techniques. While acknowledging that the current implementationof the method is prohibitively expensive for many deep-learning applications,the high cost may already be justified in specific fields like medicalpredictions or astrophysics, where a reliable uncertainty estimate for a singleprediction is essential. This work highlights the significant potential of alikelihood-ratio-based uncertainty estimate and establishes a promising avenuefor future research.

Likelihood-ratio-based confidence intervals for neural networks