Artificial Neural Network Training Using Differential Evolutionary Algorithm for Classification

Si, Tapas; Hazra, Simanta; Jana, Nanda Dulal

doi:10.1007/978-3-642-27443-5_88

Cited by 14 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SDE gives better results when compared to training ANN by GA algorithm and standard DE on four sets of the UCI dataset. Si et al [25] presented a DEGL approach to combine global and local mutation steps to create a candidate population vector using the mutation probability adaptation to balance the searchability. They tested the method on four benchmark functions and seven classification problems.…”

Section: Training Neural Network Using Differential Evolutionmentioning

confidence: 99%

An Enhanced Differential Evolution Algorithm With Adaptive Weight Bounds for Efficient Training of Neural Networks

Limtrakul

Wetweerapong

2023

IAPGOS

View full text Add to dashboard Cite

Artificial neural networks are essential intelligent tools for various learning tasks. Training them is challenging due to the nature of the data set, many training weights, and their dependency, which gives rise to a complicated high-dimensional error function for minimization. Thus, global optimization methods have become an alternative approach. Many variants of differential evolution (DE) have been applied as training methods to approximate the weights of a neural network. However, empirical studies show that they suffer from generally fixed weight bounds. In this research, we propose an enhanced differential evolution algorithm with adaptive weight bound adjustment (DEAW) for the efficient training of neural networks. The DEAW algorithm uses small initial weight bounds and adaptive adjustment in the mutation process. It gradually extends the bounds when a component of a mutant vector reaches its limits. We also experiment with using several scales of an activation function with the DEAW algorithm. Then, we apply the proposed method with its suitable setting to solve function approximation problems. DEAW can achieve satisfactory results compared to exact solutions.

show abstract

Section: Training Neural Network Using Differential Evolutionmentioning

confidence: 99%

An Enhanced Differential Evolution Algorithm With Adaptive Weight Bounds for Efficient Training of Neural Networks

Limtrakul

Wetweerapong

2023

IAPGOS

View full text Add to dashboard Cite

show abstract

“…The difficulty is associated mainly with the non-linearity of the problem that the network is meant to solve, the lack of knowledge regarding the best set of weights and biases, and the dependency of the performance of the training algorithm on the architectural aspects of the network (specifically, the topology and activation functions of the neurons). Hence, given their utility as alternatives to backpropagation and its variants [21], heuristic search algorithms were used to optimize ANNs [26,18,3,28].…”

Section: Prior Related Workmentioning

confidence: 99%

A Greedy Iterative Layered Framework for Training Feed Forward Neural Networks

Custode

Tecce

Bakurov

et al. 2020

Applications of Evolutionary Computation

View full text Add to dashboard Cite

In recent years neuroevolution has become a dynamic and rapidly growing research field. Interest in this discipline is motivated by the need to create ad-hoc networks, the topology and parameters of which are optimized, according to the particular problem at hand. Although neuroevolution-based techniques can contribute fundamentally to improving the performance of artificial neural networks (ANNs), they present a drawback, related to the massive amount of computational resources needed. This paper proposes a novel population-based framework, aimed at finding the optimal set of synaptic weights for ANNs. The proposed method partitions the weights of a given network and, using an optimization heuristic, trains one layer at each step while "freezing" the remaining weights. In the experimental study, particle swarm optimization (PSO) was used as the underlying optimizer within the framework and its performance was compared against the standard training (i.e., training that considers the whole set of weights) of the network with PSO and the backward propagation of the errors (backpropagation). Results show that the subsequent training of sub-spaces reduces training time, achieves better generalizability, and leads to the exhibition of smaller variance in the architectural aspects of the network.

show abstract

“…At the same time, Mirjalili et al [23] introduced a combination of the PSO and GSA to optimize the FNN, where they presented an acceleration coefficient in GSA to improve the performance of the overall algorithm. Si et al [24] developed a differential evolution (DE)-based method to search for the ANN's synaptic weight coefficients' optimal values. Shaw and Kinsner [25] presented the simulated annealing (SA) based on a chaotic strategy to train FNN, to mitigate the possibility of sticking in the local optima.…”

Section: Introductionmentioning

confidence: 99%

COVID-19 Forecasting Based on an Improved Interior Search Algorithm and Multilayer Feed-Forward Neural Network

Rizk‐Allah

Hassanien²

2021

Studies in Computational Intelligence

View full text Add to dashboard Cite

COVID-19 is a novel coronavirus that was emerged in December 2019 within Wuhan, China. As the crisis of its severe, increasing dynamic outbreak in all parts of the globe, the forecast maps and analysis of confirmed cases (CS) becomes a vital excellent changeling task. In this study, a new forecasting model is presented to analyze and forecast the CS of COVID-19 for the coming days based on the reported data since 22 January 2020. The proposed forecasting model, named ISACL-MFNN, integrates an improved interior search algorithm (ISA) based on chaotic learning (CL) strategy into a multilayer feed-forward neural network (MFNN). The ISACL incorporates the CL strategy to enhance ISA's performance and avoid the trapping in the local optima. This methodology is intended to train the neural network by tuning its parameters to optimal values and thus achieving high-accuracy level regarding forecasted results. The ISACL-MFNN model is investigated on the official data of the COVID-19 reported by the World Health Organization (WHO) to analyze the confirmed cases for the upcoming days. The performance regarding the proposed forecasting model is validated and assessed by introducing some indices, including the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) and the comparisons with other optimization algorithms are presented. The proposed model is investigated on the most affected countries (i.e., USA, Italy, and Spain). The experimental simulations illustrate that the proposed ISACL-MFNN provides promising performance rather than the other algorithms while forecasting the candidate countries' task.

show abstract

Artificial Neural Network Training Using Differential Evolutionary Algorithm for Classification

Cited by 14 publications

References 8 publications

An Enhanced Differential Evolution Algorithm With Adaptive Weight Bounds for Efficient Training of Neural Networks

An Enhanced Differential Evolution Algorithm With Adaptive Weight Bounds for Efficient Training of Neural Networks

A Greedy Iterative Layered Framework for Training Feed Forward Neural Networks

COVID-19 Forecasting Based on an Improved Interior Search Algorithm and Multilayer Feed-Forward Neural Network

Contact Info

Product

Resources

About