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

Automated ranking of pre-trained Deep Neural Networks (DNNs) reduces therequired time for selecting optimal pre-trained DNN and boost theclassification performance in transfer learning. In this paper, we introduce anovel algorithm to rank pre-trained DNNs by applying a straightforwarddistance-based complexity measure named Separation Index (SI) to the targetdataset. For this purpose, at first, a background about the SI is given andthen the automated ranking algorithm is explained. In this algorithm, the SI iscomputed for the target dataset which passes from the feature extracting partsof pre-trained DNNs. Then, by descending sort of the computed SIs, thepre-trained DNNs are ranked, easily. In this ranking method, the best DNN makesmaximum SI on the target dataset and a few pre-trained DNNs may be rejected inthe case of their sufficiently low computed SIs. The efficiency of the proposedalgorithm is evaluated by using three challenging datasets including Linnaeus5, Breast Cancer Images, and COVID-CT. For the two first case studies, theresults of the proposed algorithm exactly match with the ranking of the trainedDNNs by the accuracy on the target dataset. For the third case study, despiteusing different preprocessing on the target data, the ranking of the algorithmhas a high correlation with the ranking resulted from classification accuracy.

Ranking and Rejecting of Pre-Trained Deep Neural Networks in Transfer Learning based on Separation Index