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

Image classification is a difficult machine learning task, whereConvolutional Neural Networks (CNNs) have been applied for over 20 years inorder to solve the problem. In recent years, instead of the traditional way ofonly connecting the current layer with its next layer, shortcut connectionshave been proposed to connect the current layer with its forward layers apartfrom its next layer, which has been proved to be able to facilitate thetraining process of deep CNNs. However, there are various ways to build theshortcut connections, it is hard to manually design the best shortcutconnections when solving a particular problem, especially given the design ofthe network architecture is already very challenging.  In this paper, a hybrid evolutionary computation (EC) method is proposed to\textit{automatically} evolve both the architecture of deep CNNs and theshortcut connections. Three major contributions of this work are: Firstly, anew encoding strategy is proposed to encode a CNN, where the architecture andthe shortcut connections are encoded separately; Secondly, a hybrid two-levelEC method, which combines particle swarm optimisation and genetic algorithms,is developed to search for the optimal CNNs; Lastly, an adjustable learningrate is introduced for the fitness evaluations, which provides a betterlearning rate for the training process given a fixed number of epochs. Theproposed algorithm is evaluated on three widely used benchmark datasets ofimage classification and compared with 12 peer Non-EC based competitors and oneEC based competitor. The experimental results demonstrate that the proposedmethod outperforms all of the peer competitors in terms of classificationaccuracy.

A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks