| تعداد نشریات | 63 |
| تعداد شمارهها | 2,262 |
| تعداد مقالات | 18,632 |
| تعداد مشاهده مقاله | 57,740,340 |
| تعداد دریافت فایل اصل مقاله | 29,557,561 |
On weight and variance uncertainty in neural networks for regression tasks | ||
| Journal of Data Science and Modeling | ||
| مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 13 اسفند 1404 اصل مقاله (733.29 K) | ||
| نوع مقاله: Research Manuscript | ||
| شناسه دیجیتال (DOI): 10.22054/jdsm.2026.88820.1080 | ||
| نویسندگان | ||
| Morteza Amini* 1؛ Moein Monemi2؛ Mahmoud Taheri2؛ Mohammad Arashi3 | ||
| 1Department of Statistics, School of Mathematics, Statistics Aand Computer Science, College of Science, University of Tehran | ||
| 2School of Engineering Science, College of Engineering, University of Tehran, Tehran, Iran | ||
| 3Department of Statistics, Faculty of Mathematical Sciences, Ferdowsi University of Mashhad, P.O. Box 1159, Mashhad 91775, Iran | ||
| چکیده | ||
| We investigate the problem of weight uncertainty originally proposed by [Blundell et al. (2015). Weight uncertainty in neural networks. In International conference on machine learning, 1613-1622, PMLR.] in the context of neural networks designed for regression tasks, and we extend their framework by incorporating variance uncertainty into the model. Our analysis demonstrates that explicitly modeling uncertainty in the variance parameter can significantly enhance the predictive performance of Bayesian neural networks. By considering a full posterior distribution over the variance, the model achieves improved generalization compared to approaches that treat variance as fixed or deterministic. We evaluate the generalization capability of our proposed approach through a function approximation example and further validate it on the riboflavin genetic dataset. Our exploration encompasses both fully connected dense networks and dropout neural networks, employing Gaussian and spike-and-slab priors respectively for the network weights, providing a comprehensive assessment of how variance uncertainty affects model performance across different architectural choices. | ||
| کلیدواژهها | ||
| Bayesian neural networks؛ Variational Bayes؛ Kullback-Leibler divergence؛ posterior distribution؛ Regression task؛ variance uncertainty | ||
|
آمار تعداد مشاهده مقاله: 18 تعداد دریافت فایل اصل مقاله: 11 |
||