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

Machine learning (ML) solutions are prevalent in many applications. However,many challenges exist in making these solutions business-grade. For instance,maintaining the error rate of the underlying ML models at an acceptably lowlevel. Typically, the true relationship between feature inputs and the targetfeature to be predicted is uncertain, and hence statistical in nature. Theapproach we propose is to separate the observations that are the most likely tobe predicted incorrectly into 'attention sets'. These can directly aid modeldiagnosis and improvement, and be used to decide on alternative courses ofaction for these problematic observations. We present several algorithms(`strategies') for determining optimal rules to separate these observations. Inparticular, we prefer strategies that use feature-based slicing because theyare human-interpretable, model-agnostic, and require minimal supplementaryinputs or knowledge. In addition, we show that these strategies outperformseveral common baselines, such as selecting observations with predictionconfidence below a threshold. To evaluate strategies, we introduce metrics tomeasure various desired qualities, such as their performance, stability, andgeneralizability to unseen data; the strategies are evaluated on severalpublicly-available datasets. We use TOPSIS, a Multiple Criteria Decision Makingmethod, to aggregate these metrics into a single quality score for eachstrategy, to allow comparison.

Automatic Generation of Attention Rules For Containment of Machine Learning Model Errors