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

When training Convolutional Neural Networks (CNNs) there is a large emphasison creating efficient optimization algorithms and highly accurate networks. Thestate-of-the-art method of optimizing the networks is done by using gradientdescent algorithms, such as Stochastic Gradient Descent (SGD). However, thereare some limitations presented when using gradient descent methods. The majordrawback is the lack of exploration, and over-reliance on exploitation. Hence,this research aims to analyze an alternative approach to optimizing neuralnetwork (NN) weights, with the use of population-based metaheuristicalgorithms. A hybrid between Grey Wolf Optimizer (GWO) and Genetic Algorithms(GA) is explored, in conjunction with SGD; producing a Genetically ModifiedWolf optimization algorithm boosted with SGD (GMW-SGD). This algorithm allowsfor a combination between exploitation and exploration, whilst also tacklingthe issue of high-dimensionality, affecting the performance of standardmetaheuristic algorithms. The proposed algorithm was trained and tested onCIFAR-10 where it performs comparably to the SGD algorithm, reaching high testaccuracy, and significantly outperforms standard metaheuristic algorithms.

Genetically Modified Wolf Optimization with Stochastic Gradient Descent for Optimising Deep Neural Networks