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

Neural networks (NNs) have shown high predictive performance, however, withshortcomings. Firstly, the reasons behind the classifications are not fullyunderstood. Several explanation methods have been developed, but they do notprovide mechanisms for users to interact with the explanations. Explanationsare social, meaning they are a transfer of knowledge through interactions.Nonetheless, current explanation methods contribute only to one-waycommunication. Secondly, NNs tend to be overconfident, providing unreasonableuncertainty estimates on out-of-distribution observations. We overcome thesedifficulties by training a Bayesian convolutional neural network (CNN) thatuses explanation feedback. After training, the model presents explanations oftraining sample classifications to an annotator. Based on the providedinformation, the annotator can accept or reject the explanations by providingfeedback. Our proposed method utilizes this feedback for fine-tuning to correctthe model such that the explanations and classifications improve. We useexisting CNN architectures to demonstrate the method's effectiveness on one toydataset (decoy MNIST) and two real-world datasets (Dogs vs. Cats and ISIC skincancer). The experiments indicate that few annotated explanations andfine-tuning epochs are needed to improve the model and predictive performance,making the model more trustworthy and understandable.

Correcting Classification: A Bayesian Framework Using Explanation Feedback to Improve Classification Abilities