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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

These days deep learning is the fastest-growing area in the field of MachineLearning. Convolutional Neural Networks are currently the main tool used forimage analysis and classification purposes. Although great achievements andperspectives, deep neural networks and accompanying learning algorithms havesome relevant challenges to tackle. In this paper, we have focused on the mostfrequently mentioned problem in the field of machine learning, that isrelatively poor generalization abilities. Partial remedies for this areregularization techniques e.g. dropout, batch normalization, weight decay,transfer learning, early stopping and data augmentation. In this paper, we havefocused on data augmentation. We propose to use a method based on a neuralstyle transfer, which allows generating new unlabeled images of a highperceptual quality that combine the content of a base image with the appearanceof another one. In a proposed approach, the newly created images are describedwith pseudo-labels, and then used as a training dataset. Real, labeled imagesare divided into the validation and test set. We validated the proposed methodon a challenging skin lesion classification case study. Four representativeneural architectures are examined. Obtained results show the strong potentialof the proposed approach.

Style transfer-based image synthesis as an efficient regularization technique in deep learning