Restricted Bayesian Neural Network
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913304450957312 |
|---|---|
| author | Ganguly, Sourav Bhattacharjee, Saprativa |
| author_facet | Ganguly, Sourav Bhattacharjee, Saprativa |
| contents | Modern deep learning tools are remarkably effective in addressing intricate problems. However, their operation as black-box models introduces increased uncertainty in predictions. Additionally, they contend with various challenges, including the need for substantial storage space in large networks, issues of overfitting, underfitting, vanishing gradients, and more. This study explores the concept of Bayesian Neural Networks, presenting a novel architecture designed to significantly alleviate the storage space complexity of a network. Furthermore, we introduce an algorithm adept at efficiently handling uncertainties, ensuring robust convergence values without becoming trapped in local optima, particularly when the objective function lacks perfect convexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04810 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Restricted Bayesian Neural Network Ganguly, Sourav Bhattacharjee, Saprativa Machine Learning Artificial Intelligence Neural and Evolutionary Computing Modern deep learning tools are remarkably effective in addressing intricate problems. However, their operation as black-box models introduces increased uncertainty in predictions. Additionally, they contend with various challenges, including the need for substantial storage space in large networks, issues of overfitting, underfitting, vanishing gradients, and more. This study explores the concept of Bayesian Neural Networks, presenting a novel architecture designed to significantly alleviate the storage space complexity of a network. Furthermore, we introduce an algorithm adept at efficiently handling uncertainties, ensuring robust convergence values without becoming trapped in local optima, particularly when the objective function lacks perfect convexity. |
| title | Restricted Bayesian Neural Network |
| topic | Machine Learning Artificial Intelligence Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2403.04810 |