Differential Evolution-based Neural Network Training Incorporating a Centroid-based Strategy and Dynamic Opposition-based Learning

Training multi-layer neural networks (MLNNs), a challenging task, involves finding appropriate weights and biases. MLNN training is important since the performance of MLNNs is mainly dependent on these network parameters. However, conventional algorithms such as gradient-based methods, while extensively used for MLNN training, suffer from drawbacks such as a tendency to getting stuck in local optima. Population-based metaheuristic algorithms can be used to overcome these problems. In this paper, we propose a novel MLNN training algorithm, CenDE-DOBL, that is based on differential evolution (DE), a centroid-based strategy (Cen-S), and dynamic opposition-based learning (DOBL). The Cen-S approach employs the centroid of the best individuals as a member of population, while other members are updated using standard crossover and mutation operators. This improves exploitation since the new member is obtained based on the best individuals, while the employed DOBL strategy, which uses the opposite of an individual, leads to enhanced exploration. Our extensive experiments compare CenDE-DOBL to 26 conventional and population-based algorithms and confirm it to provide excellent MLNN training performance.

READ FULL TEXT
research
05/04/2023

A Cluster-Based Opposition Differential Evolution Algorithm Boosted by a Local Search for ECG Signal Classification

Electrocardiogram (ECG) signals are recordings of the heart's electrical...
research
09/08/2017

Opposition based Ensemble Micro Differential Evolution

Differential evolution (DE) algorithm with a small population size is ca...
research
05/04/2013

On Comparison between Evolutionary Programming Network-based Learning and Novel Evolution Strategy Algorithm-based Learning

This paper presents two different evolutionary systems - Evolutionary Pr...
research
11/20/2020

Multi-population differential evolution-assisted Harris hawks optimization: Framework and case studies

The first powerful variant of the Harris hawks optimization (HHO) is pro...
research
07/04/2021

Autoencoder based Randomized Learning of Feedforward Neural Networks for Regression

Feedforward neural networks are widely used as universal predictive mode...
research
08/16/2021

Evaluation of constraint in photovoltaic cells using ensemble multi-strategy shuffled frog leading algorithms

The efficient identification of the unknown and changeable photovoltaic ...

Please sign up or login with your details

Forgot password? Click here to reset