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

Training multiple-layered deep neural networks (DNNs) is difficult. Thestandard practice of using a large number of samples for training often doesnot improve the performance of a DNN to a satisfactory level. Thus, asystematic training approach is needed. To address this need, we introduce aninnovative approach of using metamorphic relations (MRs) as "knowledgecarriers" to train DNNs. Based on the concept of metamorphic testing and MRs(which play the role of a test oracle in software testing), we make use of thenotion of metamorphic group of inputs as concrete instances of MRs (which areabstractions of knowledge) to train a DNN in a systematic and effective manner.To verify the viability of our training approach, we have conducted apreliminary experiment to compare the performance of two DNNs: one trained withMRs and the other trained without MRs. We found that the DNN trained with MRshas delivered a better performance, thereby confirming that our approach ofusing MRs as knowledge carriers to train DNNs is promising. More work andstudies, however, are needed to solidify and leverage this approach to generatewidespread impact on effective DNN training.

Use of Metamorphic Relations as Knowledge Carriers to Train Deep Neural Networks