Metaheuristic design of feedforward neural networks: A review of two decades of research

VK Ojha, A Abraham, V Snášel - Engineering Applications of Artificial …, 2017 - Elsevier
Over the past two decades, the feedforward neural network (FNN) optimization has been a
key interest among the researchers and practitioners of multiple disciplines. The FNN …

Particle swarm optimization of deep neural networks architectures for image classification

FEF Junior, GG Yen - Swarm and Evolutionary Computation, 2019 - Elsevier
Deep neural networks have been shown to outperform classical machine learning
algorithms in solving real-world problems. However, the most successful deep neural …

Comparative analysis of low discrepancy sequence-based initialization approaches using population-based algorithms for solving the global optimization problems

WH Bangyal, K Nisar, AAB Ag. Ibrahim, MR Haque… - Applied Sciences, 2021 - mdpi.com
Metaheuristic algorithms have been widely used to solve diverse kinds of optimization
problems. For an optimization problem, population initialization plays a significant role in …

Optimal design of convolutional neural network architectures using teaching–learning-based optimization for image classification

KM Ang, ESM El-Kenawy, AA Abdelhamid, A Ibrahim… - Symmetry, 2022 - mdpi.com
Convolutional neural networks (CNNs) have exhibited significant performance gains over
conventional machine learning techniques in solving various real-life problems in …

A modified particle swarm optimization algorithm for optimizing artificial neural network in classification tasks

KM Ang, CE Chow, ESM El-Kenawy, AA Abdelhamid… - Processes, 2022 - mdpi.com
Artificial neural networks (ANNs) have achieved great success in performing machine
learning tasks, including classification, regression, prediction, image processing, image …

Evolutionary artificial neural networks by multi-dimensional particle swarm optimization

S Kiranyaz, T Ince, A Yildirim, M Gabbouj - Neural networks, 2009 - Elsevier
In this paper, we propose a novel technique for the automatic design of Artificial Neural
Networks (ANNs) by evolving to the optimal network configuration (s) within an architecture …

Advances of metaheuristic algorithms in training neural networks for industrial applications

HY Chong, HJ Yap, SC Tan, KS Yap, SY Wong - Soft Computing, 2021 - Springer
In recent decades, researches on optimizing the parameter of the artificial neural network
(ANN) model has attracted significant attention from researchers. Hybridization of superior …

A hybrid algorithm for artificial neural network training

M Yaghini, MM Khoshraftar, M Fallahi - Engineering Applications of …, 2013 - Elsevier
Artificial neural network (ANN) training is one of the major challenges in using a prediction
model based on ANN. Gradient based algorithms are the most frequent training algorithms …

An improved swarm optimized functional link artificial neural network (ISO-FLANN) for classification

S Dehuri, R Roy, SB Cho, A Ghosh - Journal of Systems and Software, 2012 - Elsevier
Multilayer perceptron (MLP)(trained with back propagation learning algorithm) takes large
computational time. The complexity of the network increases as the number of layers and …

Improving the classification accuracy of melanoma detection by performing feature selection using binary Harris hawks optimization algorithm

P Bansal, A Vanjani, A Mehta, JC Kavitha, S Kumar - Soft Computing, 2022 - Springer
Out of the various types of skin cancers, melanoma is observed to be the most malignant
and fatal type. Early detection of melanoma increases the chances of survival which …