| Title of Article |
Artificial neural network optimization using differential evolution algorithm with adaptive weight bound adjustment for patter classification |
| Date of Acceptance |
8 February 2023 |
| Journal |
| Title of Journal |
International Journal of Mathematics and Computer Science |
| Standard |
SCOPUS |
| Institute of Journal |
Badih Ghusayni |
| ISBN/ISSN |
1814-0432 |
| Volume |
18 |
| Issue |
2 |
| Month |
February |
| Year of Publication |
2023 |
| Page |
415-427 |
| Abstract |
Artificial neural network (ANN) is a popular machine learning technique applied to various advanced applications of artificial intelligence (AI). In this work, a differential evolution algorithm with adaptive weight bound adjustment (DEAW) is used to optimize the neural networks for solving classification problems. The DEAW algorithm initials the weights in a small range of bounds and gradually expands them in the mutation step when needed. The experiments are performed on five synthesis scatter-points datasets and four real-world UCI datasets to compare with other well-known evolutionary algorithms: harmony search, ant colony optimization, and self-adaptive differential evolution. The results show that the DEAW method is comparable to the other algorithms and performs better in several cases. |
| Keyword |
Neural network, Differential Evolution, Training Neural Network, Classification. |
| Author |
|
| Reviewing Status |
มีผู้ประเมินอิสระ |
| Status |
ได้รับการตอบรับให้ตีพิมพ์ |
| Level of Publication |
นานาชาติ |
| citation |
false |
| Part of thesis |
true |
| Attach file |
|
| Citation |
0
|
|
|
Publication
Journal Publication
ไทย