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

Tabular biomedical data is often high-dimensional but with a very smallnumber of samples. Although recent work showed that well-regularised simpleneural networks could outperform more sophisticated architectures on tabulardata, they are still prone to overfitting on tiny datasets with manypotentially irrelevant features. To combat these issues, we propose WeightPredictor Network with Feature Selection (WPFS) for learning neural networksfrom high-dimensional and small sample data by reducing the number of learnableparameters and simultaneously performing feature selection. In addition to theclassification network, WPFS uses two small auxiliary networks that togetheroutput the weights of the first layer of the classification model. We evaluateon nine real-world biomedical datasets and demonstrate that WPFS outperformsother standard as well as more recent methods typically applied to tabulardata. Furthermore, we investigate the proposed feature selection mechanism andshow that it improves performance while providing useful insights into thelearning task.

Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data