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

Convolutional neural network (CNN) models have seen advanced improvements inperformance in various domains, but lack of interpretability is a major barrierto assurance and regulation during operation for acceptance and deployment ofAI-assisted applications. There have been many works on input interpretabilityfocusing on analyzing the input-output relations, but the internal logic ofmodels has not been clarified in the current mainstream interpretabilitymethods. In this study, we propose a novel hybrid CNN-interpreter through: (1)An original forward propagation mechanism to examine the layer-specificprediction results for local interpretability. (2) A new globalinterpretability that indicates the feature correlation and filter importanceeffects. By combining the local and global interpretabilities, hybridCNN-interpreter enables us to have a solid understanding and monitoring ofmodel context during the whole learning process with detailed and consistentrepresentations. Finally, the proposed interpretabilities have beendemonstrated to adapt to various CNN-based model structures.

Hybrid CNN -Interpreter: Interpret local and global contexts for CNN-based Models