2023
DOI: 10.3390/electronics12061453
|View full text |Cite
|
Sign up to set email alerts
|

Applying Monte Carlo Dropout to Quantify the Uncertainty of Skip Connection-Based Convolutional Neural Networks Optimized by Big Data

Abstract: Although Deep Learning (DL) models have been introduced in various fields as effective prediction tools, they often do not care about uncertainty. This can be a barrier to their adoption in real-world applications. The current paper aims to apply and evaluate Monte Carlo (MC) dropout, a computationally efficient approach, to investigate the reliability of several skip connection-based Convolutional Neural Network (CNN) models while keeping their high accuracy. To do so, a high-dimensional regression problem is… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
4

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(2 citation statements)
references
References 17 publications
0
2
0
Order By: Relevance
“…Recently, a technique called MC-dropout (MCD) was created that is computationally more effective [25][26][27]. It is possible to think of a NN with any number of hidden layers as a bayesian approximation problem of the probabilistic deep gaussian process if dropout is employed before the weight layers [24,26].…”
Section: Introductionmentioning
confidence: 99%
“…Recently, a technique called MC-dropout (MCD) was created that is computationally more effective [25][26][27]. It is possible to think of a NN with any number of hidden layers as a bayesian approximation problem of the probabilistic deep gaussian process if dropout is employed before the weight layers [24,26].…”
Section: Introductionmentioning
confidence: 99%
“…For instance, in the realm of MRI imaging, Sherine Brahma et al [33] emphasized the use of deep learning algorithms to enhance image reconstruction, while stressing the importance of obtaining a metric to identify artifacts [33]. Similarly, Choubineh et al [34] applied Monte Carlo dropout to assess the reliability of several CNN models in the context of subterranean fluid flow modeling, emphasizing the importance of considering the uncertainty in deep learning models [34]. In the domain of EEG-based predictions, Li et al [35] introduced a patient-specific seizure prediction framework that considers model uncertainty and proposed a modified Monte Carlo dropout strategy to enhance the reliability of DNN-based models [35].…”
Section: Introductionmentioning
confidence: 99%