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

The use of deep neural networks to make high risk decisions creates a needfor global and local explanations so that users and experts have confidence inthe modeling algorithms. We introduce a novel technique to find global andlocal explanations for time series data used in binary classification machinelearning systems. We identify the most salient of the original features used bya black box model to distinguish between classes. The explanation can be madeon categorical, continuous, and time series data and can be generalized to anybinary classification model. The analysis is conducted on time series data totrain a long short-term memory deep neural network and uses the time dependentstructure of the underlying features in the explanation. The proposed techniqueattributes weights to features to explain an observations risk of belonging toa class as a multiplicative factor of a base hazard rate. We use a variation ofthe Cox Proportional Hazards regression, a Generalized Additive Model, toexplain the effect of variables upon the probability of an in-class responsefor a score output from the black box model. The covariates incorporate timedependence structure in the features so the explanation is inclusive of theunderlying time series data structure.

Local Score Dependent Model Explanation for Time Dependent Covariates