Multi Mother Wavelet Neural Network Based on Genetic Algorithm for 1d and 2d Functions’ Approximation

Chihaoui, Mejda; Bellil, Wajdi; Amar, Chokri Ben

doi:10.5220/0003083704290434

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The iteration is set to 30000. In these experiments, the DEAW approximates the 2D-function 𝑓 7 , 𝑓 8 to compare with MMWNN-GA method in [5]. As seen in table 10, the error rate of our proposed method reaches 4.41E-03 which is higher than the MMWNN-GA method.…”

Section: B Comparison On 2d-function Approximation Problemsmentioning

confidence: 92%

“…For more comparison tests, we applied the DEAW algorithm to approximate the 2D functions which are used in [5]. The functions are represented as follows.…”

Section: B Comparison On 2d-function Approximation Problemsmentioning

confidence: 99%

“…Table 10. Comparison results of 2D-function 𝑓 7 using MMWNN-GA [5] Next, the DEAW algorithm is demonstrated with the 2Dfunction 𝑓 8 . The results in table 11 show that our proposed simple method approximates accurately as well as MMWNN-GA method.…”

Section: B Comparison On 2d-function Approximation Problemsmentioning

confidence: 99%

See 2 more Smart Citations

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: B Comparison On 2d-function Approximation Problemsmentioning

confidence: 92%

“…For more comparison tests, we applied the DEAW algorithm to approximate the 2D functions which are used in [5]. The functions are represented as follows.…”

Section: B Comparison On 2d-function Approximation Problemsmentioning

confidence: 99%