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

Continual learning can enable neural networks to evolve by learning new taskssequentially in task-changing scenarios. However, two general and relatedchallenges should be overcome in further research before we apply thistechnique to real-world applications. Firstly, newly collected novelties fromthe data stream in applications could contain anomalies that are meaninglessfor continual learning. Instead of viewing them as a new task for updating, wehave to filter out such anomalies to reduce the disturbance of extremelyhigh-entropy data for the progression of convergence. Secondly, fewer effortshave been put into research regarding the explainability of continual learning,which leads to a lack of transparency and credibility of the updated neuralnetworks. Elaborated explanations about the process and result of continuallearning can help experts in judgment and making decisions. Therefore, wepropose the conceptual design of an explainability module with experts in theloop based on techniques, such as dimension reduction, visualization, andevaluation strategies. This work aims to overcome the mentioned challenges bysufficiently explaining and visualizing the identified anomalies and theupdated neural network. With the help of this module, experts can be moreconfident in decision-making regarding anomaly filtering, dynamic adjustment ofhyperparameters, data backup, etc.

Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning