•  
  •  
 

Abstract

Owing to the increasing interest in artificial neural networks(ANNs)acrossvarious fields of study, many studies have focused onenhancing theirperformance through theutilisationof differentlearning algorithms. This study examinesthe use of the Whale Optimization Algorithm (WOA) as a training algorithm toimprove the classification accuracy ofANNsGetting artificial neural networks (ANNs) to categorize things accurately requires good model design -you need to pick the right structure, training algorithm, and activation functions. For this project, the researchers tested using the Whale OptimizationAlgorithm (WOA) method to train the ANN models instead of the commonly used backpropagation approach. They gathered 10 real-world datasets from the UCI machine learning repository to train and compare models on. When they compared ANNs trained with WOA against standard backprop-trained ANNs, the WOA ones did better at classifying the data. Using the whale algorithm to optimize the models led to higher accuracy in predicting the categories for the datasets. The results showed that fine-tuning an ANN with WOA outperformed just using regular backpropagation training. The classification accuracy of a WOA-trained ANN was compared with that of a backpropagation-trained ANN, and the results showed that the WOA-trained ANN exhibited superior performance.

Download

Share

COinS