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

In this paper, we propose a hybrid model combining genetic algorithm and hillclimbing algorithm for optimizing Convolutional Neural Networks (CNNs) on theCIFAR-100 dataset. The proposed model utilizes a population of chromosomes thatrepresent the hyperparameters of the CNN model. The genetic algorithm is usedfor selecting and breeding the fittest chromosomes to generate new offspring.The hill climbing algorithm is then applied to the offspring to furtheroptimize their hyperparameters. The mutation operation is introduced todiversify the population and to prevent the algorithm from getting stuck inlocal optima. The Genetic Algorithm is used for global search and explorationof the search space, while Hill Climbing is used for local optimization ofpromising solutions. The objective function is the accuracy of the trainedneural network on the CIFAR-100 test set. The performance of the hybrid modelis evaluated by comparing it with the standard genetic algorithm andhill-climbing algorithm. The experimental results demonstrate that the proposedhybrid model achieves better accuracy with fewer generations compared to thestandard algorithms. Therefore, the proposed hybrid model can be a promisingapproach for optimizing CNN models on large datasets.

Hybrid Genetic Algorithm and Hill Climbing Optimization for the Neural Network