|
|
Publication
|
| Title of Article |
AN ENHANCED DIFFERENTIAL EVOLUTION ALGORITHM WITH ADAPTIVE WEIGHT BOUNDS FOR EFFICIENT TRAINING OF NEURAL NETWORKS |
| Date of Acceptance |
13 March 2023 |
| Journal |
| Title of Journal |
Informatics, Control, Measurement in Economy and Environmental Protection („Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska” – IAPGOS) |
| Standard |
SCOPUS |
| Institute of Journal |
Lublin University of Technology |
| ISBN/ISSN |
2391-6761 (on-line), 2083-0157 (print) |
| Volume |
13 |
| Issue |
1 |
| Month |
March |
| Year of Publication |
2023 |
| Page |
4-13 |
| Abstract |
Artificial neural networks are essential intelligent tools for various learning tasks.Training them is challenging due to the natureof 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 applythe proposed method with its suitable setting to solve function approximation problems. DEAW can achieve satisfactory results compared to exact solutions. |
| Keyword |
neural network, differential evolution, training neural network, function approximation |
| Author |
|
| Reviewing Status |
มีผู้ประเมินอิสระ |
| Status |
ตีพิมพ์แล้ว |
| Level of Publication |
นานาชาติ |
| citation |
false |
| Part of thesis |
true |
| Attach file |
|
| Citation |
0
|
|
|
|
|
|
|
|
|
Journal Publication
ไทย