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

Choubineh, Abouzar; Chen, Jie; Coenen, Frans; Ma, Fei

doi:10.3390/electronics12061453

Cited by 4 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

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%

Epistemic Uncertainty and Model Transparency in Rock Facies Classification Using Monte Carlo Dropout Deep Learning

Hossain,

Hermana,

Abdulkadir

2023

IEEE Access

View full text Add to dashboard Cite

Although Deep Learning (DL) architectures have been used as efficient prediction tools in a variety of domains, they frequently do not care about the uncertainty in the predictions. This may prevent them from being used in practical applications. In seismic reservoir characterisation, predicting facies from seismic data is typically viewed as an inverse uncertainty quantification issue. The goal of the current study is to analyse the dependability of rock facies classification model in order to quantify the uncertainty while maintaining the high accuracy by using and evaluating monte carlo dropout based deep learning (MCDL), a computationally efficient technique. The proposed method is unique since it can quantify the epistemic uncertainty of the classified facies in blind or unseen well conditioned on Seismic attributes in the bayesian approximation achieved by MCDL framework. The findings show that MC dropout is successful in terms of accuracy and reliability, with a blind test F1-scores of 98% and 82% in predicting facies from synthetic and seismic datasets respectively. Moreover, the applications in a 2D section indicate that the internal regions of the seismic sections are generally classified with less epistemic uncertainty than their boundaries, as calculated from the different realizations of the MCDL network. For comparison, a plain DL and support vector machine (SVM) are also implemented and the findings suggest that our method outperformns the other models in comparison which indicates the potential of the model to be implemented in a robust rock facies classification.

show abstract

Section: Introductionmentioning

confidence: 99%

Epistemic Uncertainty and Model Transparency in Rock Facies Classification Using Monte Carlo Dropout Deep Learning

Hossain,

Hermana,

Abdulkadir

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…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%

Why Uncertainty in Deep Learning for Traffic Flow Prediction Is Needed

Kim,

Lee

2023

Sustainability

View full text Add to dashboard Cite

Recently, traffic flow prediction has gained popularity in the implementation of intelligent transportation systems. Most of the existing models for traffic flow prediction focus on increasing the prediction performance and providing fast predictions for real-time applications. In addition, they can reveal the integrity of a prediction when an actual value is provided. However, they cannot explain prediction uncertainty. Uncertainty has recently emerged as an important problem to be solved in deep learning. To address this issue, a Monte Carlo dropout method was proposed. This method estimates the uncertainty of a traffic prediction model. Using 5,729,640 traffic data points from Seoul, the model was designed to predict both the uncertainty and measurements. Notably, it performed better than the LSTM model. Experiments were conducted to show that the values predicted by the model and their uncertainty can be estimated together without significantly decreasing the performance of the model. In addition, a normality test was performed on the traffic flow uncertainty to confirm the normality, through which a benchmark for uncertainty was presented. Following these findings, the inclusion of uncertainty provides additional insights into our model, setting a new benchmark for traffic predictions, and enhancing the capabilities of intelligent transportation systems.

show abstract

Fouling fault detection and diagnosis in district heating substations: Validation of a hybrid CNN-based PCA model with uncertainty quantification on virtual replica synthesis and real data

Jallal,

Vallée,

Lamaison

2024

Energy

View full text Add to dashboard Cite

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

Cited by 4 publications

References 17 publications

Epistemic Uncertainty and Model Transparency in Rock Facies Classification Using Monte Carlo Dropout Deep Learning

Epistemic Uncertainty and Model Transparency in Rock Facies Classification Using Monte Carlo Dropout Deep Learning

Why Uncertainty in Deep Learning for Traffic Flow Prediction Is Needed

Fouling fault detection and diagnosis in district heating substations: Validation of a hybrid CNN-based PCA model with uncertainty quantification on virtual replica synthesis and real data

Contact Info

Product

Resources

About