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

In this article, we introduce a novel variant of the Tsetlin machine (TM)that randomly drops clauses, the key learning elements of a TM. In effect, TMwith drop clause ignores a random selection of the clauses in each epoch,selected according to a predefined probability. In this way, additionalstochasticity is introduced in the learning phase of TM. To explore the effectsdrop clause has on accuracy, training time, interpretability and robustness, weconduct extensive experiments on nine benchmark datasets in natural languageprocessing~(NLP) (IMDb, R8, R52, MR and TREC) and image classification (MNIST,Fashion MNIST, CIFAR-10 and CIFAR-100). Our proposed model outperforms baselinemachine learning algorithms by a wide margin and achieves competitiveperformance in comparison with recent deep learning model such as BERT andAlexNET-DFA. In brief, we observe up to +10% increase in accuracy and 2x to 4xfaster learning compared with standard TM. We further employ the ConvolutionalTM to document interpretable results on the CIFAR datasets, visualizing how theheatmaps produced by the TM become more interpretable with drop clause. We alsoevaluate how drop clause affects learning robustness by introducing corruptionsand alterations in the image/language test data. Our results show that dropclause makes TM more robust towards such changes.

Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin Machine