Predictive Abilities of Bayesian Regularization and Levenberg–Marquardt Algorithms in Artificial Neural Networks: A Comparative Empirical Study on Social Data
The objective of this study is to compare the predictive ability of Bayesian regularization with Levenberg–Marquardt Artificial Neural Networks. To examine the best architecture of neural networks, the model was tested with one-, two-, three-, four-, and five-neuron architectures, respectively. MATL...
Uloženo v:
| Vydáno v: | Mathematical and computational applications Ročník 21; číslo 2; s. 20 |
|---|---|
| Hlavní autor: | |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
24.05.2016
|
| ISSN: | 2297-8747, 2297-8747 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Shrnutí: | The objective of this study is to compare the predictive ability of Bayesian regularization with Levenberg–Marquardt Artificial Neural Networks. To examine the best architecture of neural networks, the model was tested with one-, two-, three-, four-, and five-neuron architectures, respectively. MATLAB (2011a) was used for analyzing the Bayesian regularization and Levenberg–Marquardt learning algorithms. It is concluded that the Bayesian regularization training algorithm shows better performance than the Levenberg–Marquardt algorithm. The advantage of a Bayesian regularization artificial neural network is its ability to reveal potentially complex relationships, meaning it can be used in quantitative studies to provide a robust model. |
|---|---|
| ISSN: | 2297-8747 2297-8747 |
| DOI: | 10.3390/mca21020020 |