Journal articles: 'Deep learning with uncertainty'

1

Liu, Wei, Xiaodong Yue, Yufei Chen, and Thierry Denoeux. "Trusted Multi-View Deep Learning with Opinion Aggregation." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7585–93. http://dx.doi.org/10.1609/aaai.v36i7.20724.

Full text

Abstract:

Multi-view deep learning is performed based on the deep fusion of data from multiple sources, i.e. data with multiple views. However, due to the property differences and inconsistency of data sources, the deep learning results based on the fusion of multi-view data may be uncertain and unreliable. It is required to reduce the uncertainty in data fusion and implement the trusted multi-view deep learning. Aiming at the problem, we revisit the multi-view learning from the perspective of opinion aggregation and thereby devise a trusted multi-view deep learning method. Within this method, we adopt evidence theory to formulate the uncertainty of opinions as learning results from different data sources and measure the uncertainty of opinion aggregation as multi-view learning results through evidence accumulation. We prove that accumulating the evidences from multiple data views will decrease the uncertainty in multi-view deep learning and facilitate to achieve the trusted learning results. Experiments on various kinds of multi-view datasets verify the reliability and robustness of the proposed multi-view deep learning method.

APA, Harvard, Vancouver, ISO, and other styles

2

Oh, Dongpin, and Bonggun Shin. "Improving Evidential Deep Learning via Multi-Task Learning." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7895–903. http://dx.doi.org/10.1609/aaai.v36i7.20759.

Full text

Abstract:

The Evidential regression network (ENet) estimates a continuous target and its predictive uncertainty without costly Bayesian model averaging. However, it is possible that the target is inaccurately predicted due to the gradient shrinkage problem of the original loss function of the ENet, the negative log marginal likelihood (NLL) loss. In this paper, the objective is to improve the prediction accuracy of the ENet while maintaining its efficient uncertainty estimation by resolving the gradient shrinkage problem. A multi-task learning (MTL) framework, referred to as MT-ENet, is proposed to accomplish this aim. In the MTL, we define the Lipschitz modified mean squared error (MSE) loss function as another loss and add it to the existing NLL loss. The Lipschitz modified MSE loss is designed to mitigate the gradient conflict with the NLL loss by dynamically adjusting its Lipschitz constant. By doing so, the Lipschitz MSE loss does not disturb the uncertainty estimation of the NLL loss. The MT-ENet enhances the predictive accuracy of the ENet without losing uncertainty estimation capability on the synthetic dataset and real-world benchmarks, including drug-target affinity (DTA) regression. Furthermore, the MT-ENet shows remarkable calibration and out-of-distribution detection capability on the DTA benchmarks.

APA, Harvard, Vancouver, ISO, and other styles

3

Bajorath, Jürgen. "Understanding uncertainty in deep learning builds confidence." Artificial Intelligence in the Life Sciences 2 (December 2022): 100033. http://dx.doi.org/10.1016/j.ailsci.2022.100033.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

van den Berg, Cornelis A. T., and Ettore F. Meliadò. "Uncertainty Assessment for Deep Learning Radiotherapy Applications." Seminars in Radiation Oncology 32, no. 4 (October 2022): 304–18. http://dx.doi.org/10.1016/j.semradonc.2022.06.001.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Zheng, Rui, Shulin Zhang, Lei Liu, Yuhao Luo, and Mingzhai Sun. "Uncertainty in Bayesian deep label distribution learning." Applied Soft Computing 101 (March 2021): 107046. http://dx.doi.org/10.1016/j.asoc.2020.107046.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Lockwood, Owen, and Mei Si. "A Review of Uncertainty for Deep Reinforcement Learning." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 18, no. 1 (October 11, 2022): 155–62. http://dx.doi.org/10.1609/aiide.v18i1.21959.

Full text

Abstract:

Uncertainty is ubiquitous in games, both in the agents playing games and often in the games themselves. Working with uncertainty is therefore an important component of successful deep reinforcement learning agents. While there has been substantial effort and progress in understanding and working with uncertainty for supervised learning, the body of literature for uncertainty aware deep reinforcement learning is less developed. While many of the same problems regarding uncertainty in neural networks for supervised learning remain for reinforcement learning, there are additional sources of uncertainty due to the nature of an interactable environment. In this work, we provide an overview motivating and presenting existing techniques in uncertainty aware deep reinforcement learning. These works show empirical benefits on a variety of reinforcement learning tasks. This work serves to help to centralize the disparate results and promote future research in this area.

APA, Harvard, Vancouver, ISO, and other styles

7

Karimi, Hamed, and Reza Samavi. "Quantifying Deep Learning Model Uncertainty in Conformal Prediction." Proceedings of the AAAI Symposium Series 1, no. 1 (October 3, 2023): 142–48. http://dx.doi.org/10.1609/aaaiss.v1i1.27492.

Full text

Abstract:

Precise estimation of predictive uncertainty in deep neural networks is a critical requirement for reliable decision-making in machine learning and statistical modeling, particularly in the context of medical AI. Conformal Prediction (CP) has emerged as a promising framework for representing the model uncertainty by providing well-calibrated confidence levels for individual predictions. However, the quantification of model uncertainty in conformal prediction remains an active research area, yet to be fully addressed. In this paper, we explore state-of-the-art CP methodologies and their theoretical foundations. We propose a probabilistic approach in quantifying the model uncertainty derived from the produced prediction sets in conformal prediction and provide certified boundaries for the computed uncertainty. By doing so, we allow model uncertainty measured by CP to be compared by other uncertainty quantification methods such as Bayesian (e.g., MC-Dropout and DeepEnsemble) and Evidential approaches.

APA, Harvard, Vancouver, ISO, and other styles

8

Caldeira, João, and Brian Nord. "Deeply uncertain: comparing methods of uncertainty quantification in deep learning algorithms." Machine Learning: Science and Technology 2, no. 1 (December 4, 2020): 015002. http://dx.doi.org/10.1088/2632-2153/aba6f3.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Da Silva, Felipe Leno, Pablo Hernandez-Leal, Bilal Kartal, and Matthew E. Taylor. "Uncertainty-Aware Action Advising for Deep Reinforcement Learning Agents." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 5792–99. http://dx.doi.org/10.1609/aaai.v34i04.6036.

Full text

Abstract:

Although Reinforcement Learning (RL) has been one of the most successful approaches for learning in sequential decision making problems, the sample-complexity of RL techniques still represents a major challenge for practical applications. To combat this challenge, whenever a competent policy (e.g., either a legacy system or a human demonstrator) is available, the agent could leverage samples from this policy (advice) to improve sample-efficiency. However, advice is normally limited, hence it should ideally be directed to states where the agent is uncertain on the best action to execute. In this work, we propose Requesting Confidence-Moderated Policy advice (RCMP), an action-advising framework where the agent asks for advice when its epistemic uncertainty is high for a certain state. RCMP takes into account that the advice is limited and might be suboptimal. We also describe a technique to estimate the agent uncertainty by performing minor modifications in standard value-function-based RL methods. Our empirical evaluations show that RCMP performs better than Importance Advising, not receiving advice, and receiving it at random states in Gridworld and Atari Pong scenarios.

APA, Harvard, Vancouver, ISO, and other styles

10

Kawano, Yasufumi, Yoshiki Nota, Rinpei Mochizuki, and Yoshimitsu Aoki. "Non-Deep Active Learning for Deep Neural Networks." Sensors 22, no. 14 (July 13, 2022): 5244. http://dx.doi.org/10.3390/s22145244.

Full text

Abstract:

One way to improve annotation efficiency is active learning. The goal of active learning is to select images from many unlabeled images, where labeling will improve the accuracy of the machine learning model the most. To select the most informative unlabeled images, conventional methods use deep neural networks with a large number of computation nodes and long computation time, but we propose a non-deep neural network method that does not require any additional training for unlabeled image selection. The proposed method trains a task model on labeled images, and then the model predicts unlabeled images. Based on this prediction, an uncertainty indicator is generated for each unlabeled image. Images with a high uncertainty index are considered to have a high information content, and are selected for annotation. Our proposed method is based on a very simple and powerful idea: select samples near the decision boundary of the model. Experimental results on multiple datasets show that the proposed method achieves higher accuracy than conventional active learning methods on multiple tasks and up to 14 times faster execution time from 1.2 × 106 s to 8.3 × 104 s. The proposed method outperforms the current SoTA method by 1% accuracy on CIFAR-10.

APA, Harvard, Vancouver, ISO, and other styles

11

Gou, Xiaohong, and Xuenong He. "Deep Learning-Based Detection and Diagnosis of Subarachnoid Hemorrhage." Journal of Healthcare Engineering 2021 (November 22, 2021): 1–10. http://dx.doi.org/10.1155/2021/9639419.

Full text

Abstract:

Subarachnoid hemorrhage (SAH) is one of the critical and severe neurological diseases with high morbidity and mortality. Head computed tomography (CT) is among the preferred methods for the diagnosis of SAH, which is confirmed by CT showing high-density shadow in the subarachnoid space. Analysis of these images through a deep learning-based subarachnoid hemorrhage will reduce the approximate rate of misdiagnosis in general and missed diagnosis by clinicians in particular. Deep learning-based detection of subarachnoid hemorrhage mainly includes two tasks, i.e., subarachnoid hemorrhage classification and subarachnoid hemorrhage region segmentation. However, it is difficult to effectively judge reliability of the model and classify bleeding which is based on limited predictive probability of convolutional neural network output. Moreover, deep learning-based bleeding area segmentation requires a large amount of training data to be marked in advance and the large number of network parameters makes the model training unable to reach the optimal. To resolve these problems associated with existing models, Bayesian deep learning and neural network-based hybrid model is presented in this paper to estimate uncertainty and efficiently classify subarachnoid hemorrhage. Uncertainty estimation of the proposed model helps in judging whether the model’s prediction is reliable or not. Additionally, it is used to guide clinicians to find the neglected subarachnoid hemorrhage area. In addition, a teacher-student mechanism deep learning model was designed to introduce observational uncertainty estimation for semisupervised learning of subarachnoid hemorrhage. Observation uncertainty estimation detects the uncertain bleeding areas in CT images and then selects areas with high reliability. Finally, it uses these unlabeled data for model training purposes as well.

APA, Harvard, Vancouver, ISO, and other styles

12

Loftus, Tyler J., Benjamin Shickel, Matthew M. Ruppert, Jeremy A. Balch, Tezcan Ozrazgat-Baslanti, Patrick J. Tighe, Philip A. Efron, et al. "Uncertainty-aware deep learning in healthcare: A scoping review." PLOS Digital Health 1, no. 8 (August 10, 2022): e0000085. http://dx.doi.org/10.1371/journal.pdig.0000085.

Full text

Abstract:

Mistrust is a major barrier to implementing deep learning in healthcare settings. Entrustment could be earned by conveying model certainty, or the probability that a given model output is accurate, but the use of uncertainty estimation for deep learning entrustment is largely unexplored, and there is no consensus regarding optimal methods for quantifying uncertainty. Our purpose is to critically evaluate methods for quantifying uncertainty in deep learning for healthcare applications and propose a conceptual framework for specifying certainty of deep learning predictions. We searched Embase, MEDLINE, and PubMed databases for articles relevant to study objectives, complying with PRISMA guidelines, rated study quality using validated tools, and extracted data according to modified CHARMS criteria. Among 30 included studies, 24 described medical imaging applications. All imaging model architectures used convolutional neural networks or a variation thereof. The predominant method for quantifying uncertainty was Monte Carlo dropout, producing predictions from multiple networks for which different neurons have dropped out and measuring variance across the distribution of resulting predictions. Conformal prediction offered similar strong performance in estimating uncertainty, along with ease of interpretation and application not only to deep learning but also to other machine learning approaches. Among the six articles describing non-imaging applications, model architectures and uncertainty estimation methods were heterogeneous, but predictive performance was generally strong, and uncertainty estimation was effective in comparing modeling methods. Overall, the use of model learning curves to quantify epistemic uncertainty (attributable to model parameters) was sparse. Heterogeneity in reporting methods precluded the performance of a meta-analysis. Uncertainty estimation methods have the potential to identify rare but important misclassifications made by deep learning models and compare modeling methods, which could build patient and clinician trust in deep learning applications in healthcare. Efficient maturation of this field will require standardized guidelines for reporting performance and uncertainty metrics.

APA, Harvard, Vancouver, ISO, and other styles

13

Xu, Lei, Nengcheng Chen, Chao Yang, Hongchu Yu, and Zeqiang Chen. "Quantifying the uncertainty of precipitation forecasting using probabilistic deep learning." Hydrology and Earth System Sciences 26, no. 11 (June 14, 2022): 2923–38. http://dx.doi.org/10.5194/hess-26-2923-2022.

Full text

Abstract:

Abstract. Precipitation forecasting is an important mission in weather science. In recent years, data-driven precipitation forecasting techniques could complement numerical prediction, such as precipitation nowcasting, monthly precipitation projection and extreme precipitation event identification. In data-driven precipitation forecasting, the predictive uncertainty arises mainly from data and model uncertainties. Current deep learning forecasting methods could model the parametric uncertainty by random sampling from the parameters. However, the data uncertainty is usually ignored in the forecasting process and the derivation of predictive uncertainty is incomplete. In this study, the input data uncertainty, target data uncertainty and model uncertainty are jointly modeled in a deep learning precipitation forecasting framework to estimate the predictive uncertainty. Specifically, the data uncertainty is estimated a priori and the input uncertainty is propagated forward through model weights according to the law of error propagation. The model uncertainty is considered by sampling from the parameters and is coupled with input and target data uncertainties in the objective function during the training process. Finally, the predictive uncertainty is produced by propagating the input uncertainty in the testing process. The experimental results indicate that the proposed joint uncertainty modeling framework for precipitation forecasting exhibits better forecasting accuracy (improving RMSE by 1 %–2 % and R2 by 1 %–7 % on average) relative to several existing methods, and could reduce the predictive uncertainty by ∼28 % relative to the approach of Loquercio et al. (2020). The incorporation of data uncertainty in the objective function changes the distributions of model weights of the forecasting model and the proposed method can slightly smooth the model weights, leading to the reduction of predictive uncertainty relative to the method of Loquercio et al. (2020). The predictive accuracy is improved in the proposed method by incorporating the target data uncertainty and reducing the forecasting error of extreme precipitation. The developed joint uncertainty modeling method can be regarded as a general uncertainty modeling approach to estimate predictive uncertainty from data and model in forecasting applications.

APA, Harvard, Vancouver, ISO, and other styles

14

Pham, Nam, Sergey Fomel, and Dallas Dunlap. "Automatic channel detection using deep learning." Interpretation 7, no. 3 (August 1, 2019): SE43—SE50. http://dx.doi.org/10.1190/int-2018-0202.1.

Full text

Abstract:

We have developed a method based on an encoder-decoder convolutional neural network for automatic channel detection in 3D seismic volumes. We use two architectures borrowed from computer vision: SegNet for image segmentation together with Bayesian SegNet for uncertainty measurement. We train the network on 3D synthetic volumes and then apply it to field data. We test the proposed approach on a 3D field data set from the Browse Basin, offshore Australia, and a 3D Parihaka seismic data in New Zealand. Applying the weights estimated from training on 3D synthetic volumes to a 3D field data set accurately identifies channel geobodies without the need for any human interpretation on seismic attributes. Our proposed method also produces uncertainty volumes to quantify the trustworthiness of the detection model.

APA, Harvard, Vancouver, ISO, and other styles

15

Kabir, H. M. Dipu, Sadia Khanam, Fahime Khozeimeh, Abbas Khosravi, Subrota Kumar Mondal, Saeid Nahavandi, and U. Rajendra Acharya. "Aleatory-aware deep uncertainty quantification for transfer learning." Computers in Biology and Medicine 143 (April 2022): 105246. http://dx.doi.org/10.1016/j.compbiomed.2022.105246.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Morocho-Cayamcela, Manuel Eugenio, Martin Maier, and Wansu Lim. "Breaking Wireless Propagation Environmental Uncertainty With Deep Learning." IEEE Transactions on Wireless Communications 19, no. 8 (August 2020): 5075–87. http://dx.doi.org/10.1109/twc.2020.2986202.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Gude, Vinayaka, Steven Corns, and Suzanna Long. "Flood Prediction and Uncertainty Estimation Using Deep Learning." Water 12, no. 3 (March 21, 2020): 884. http://dx.doi.org/10.3390/w12030884.

Full text

Abstract:

Floods are a complex phenomenon that are difficult to predict because of their non-linear and dynamic nature. Therefore, flood prediction has been a key research topic in the field of hydrology. Various researchers have approached this problem using different techniques ranging from physical models to image processing, but the accuracy and time steps are not sufficient for all applications. This study explores deep learning techniques for predicting gauge height and evaluating the associated uncertainty. Gauge height data for the Meramec River in Valley Park, Missouri was used to develop and validate the model. It was found that the deep learning model was more accurate than the physical and statistical models currently in use while providing information in 15 minute increments rather than six hour increments. It was also found that the use of data sub-selection for regularization in deep learning is preferred to dropout. These results make it possible to provide more accurate and timely flood prediction for a wide variety of applications, including transportation systems.

APA, Harvard, Vancouver, ISO, and other styles

18

Pei, Zhihao, Angela M. Rojas-Arevalo, Fjalar J. de Haan, Nir Lipovetzky, and Enayat A. Moallemi. "Reinforcement learning for decision-making under deep uncertainty." Journal of Environmental Management 359 (May 2024): 120968. http://dx.doi.org/10.1016/j.jenvman.2024.120968.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Peluso, Alina, Ioana Danciu, Hong-Jun Yoon, Jamaludin Mohd Yusof, Tanmoy Bhattacharya, Adam Spannaus, Noah Schaefferkoetter, et al. "Deep learning uncertainty quantification for clinical text classification." Journal of Biomedical Informatics 149 (January 2024): 104576. http://dx.doi.org/10.1016/j.jbi.2023.104576.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Murad, Abdulmajid, Frank Alexander Kraemer, Kerstin Bach, and Gavin Taylor. "Uncertainty-aware autonomous sensing with deep reinforcement learning." Future Generation Computer Systems 156 (July 2024): 242–53. http://dx.doi.org/10.1016/j.future.2024.03.021.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Yoon, Young-In, and Hye-Young Jeong. "A Comparison of Uncertainty Quantification of Deep Learning models for Time Series." Korean Data Analysis Society 26, no. 1 (February 29, 2024): 163–74. http://dx.doi.org/10.37727/jkdas.2024.26.1.163.

Full text

Abstract:

With the advancement of artificial intelligence, machine learning, and deep learning, their applications in various industries, particularly finance, have increased. However, interpreting predictions from deep learning models poses challenges, especially in finance where result interpretation is important. This study aims to determine the uncertainty of stable deep learning models, despite changes in the model like dropout, to establish standards for reliable models and identify those detecting anomal data through model uncertainty. In the experiment, the traditional statistical model ARIMA and deep learning models mainly used for time series analysis, CNN, LSTM, MLP, and CNN-LSTM. Uncertainty was measured from a Bayesian perspective using MC Dropout. The experimental results confirmed that deep learning models performed better than statistical models for various patterns of time series data. It was observed that, even if the performance was not the best, LSTM based models exhibited low uncertainty, indicating stability. Consequently, this study highlights the importance of considering uncertainty along with accuracy in model selection. Moreover, it was confirmed that models with higher uncertainty are suitable for anomaly detection, making CNN based models particularly fitting for this purpose.

APA, Harvard, Vancouver, ISO, and other styles

22

Bhatia, Abhinav, Pradeep Varakantham, and Akshat Kumar. "Resource Constrained Deep Reinforcement Learning." Proceedings of the International Conference on Automated Planning and Scheduling 29 (May 25, 2021): 610–20. http://dx.doi.org/10.1609/icaps.v29i1.3528.

Full text

Abstract:

In urban environments, resources have to be constantly matched to the “right” locations where customer demand is present. For instance, ambulances have to be matched to base stations regularly so as to reduce response time for emergency incidents in ERS (Emergency Response Systems); vehicles (cars, bikes among others) have to be matched to docking stations to reduce lost demand in shared mobility systems. Such problems are challenging owing to the demand uncertainty, combinatorial action spaces and constraints on allocation of resources (e.g., total resources, minimum and maximum number of resources at locations and regions).Existing systems typically employ myopic and greedy optimization approaches to optimize resource allocation. Such approaches typically are unable to handle surges or variances in demand patterns well. Recent work has demonstrated the ability of Deep RL methods in adapting well to highly uncertain environments. However, existing Deep RL methods are unable to handle combinatorial action spaces and constraints on allocation of resources. To that end, we have developed three approaches on top of the well known actor-critic approach, DDPG (Deep Deterministic Policy Gradient) that are able to handle constraints on resource allocation. We also demonstrate that they are able to outperform leading approaches on simulators validated on semi-real and real data sets.

APA, Harvard, Vancouver, ISO, and other styles

23

Serpell, Cristián, Ignacio A. Araya, Carlos Valle, and Héctor Allende. "Addressing model uncertainty in probabilistic forecasting using Monte Carlo dropout." Intelligent Data Analysis 24 (December 4, 2020): 185–205. http://dx.doi.org/10.3233/ida-200015.

Full text

Abstract:

In recent years, deep learning models have been developed to address probabilistic forecasting tasks, assuming an implicit stochastic process that relates past observed values to uncertain future values. These models are capable of capturing the inherent uncertainty of the underlying process, but they ignore the model uncertainty that comes from the fact of not having infinite data. This work proposes addressing the model uncertainty problem using Monte Carlo dropout, a variational approach that assigns distributions to the weights of a neural network instead of simply using fixed values. This allows to easily adapt common deep learning models currently in use to produce better probabilistic forecasting estimates, in terms of their consideration of uncertainty. The proposal is validated for prediction intervals estimation on seven energy time series, using a popular probabilistic model called Mean Variance Estimation (MVE), as the deep model adapted using the technique.

APA, Harvard, Vancouver, ISO, and other styles

24

Silva, Felipe Leno Da, Pablo Hernandez-Leal, Bilal Kartal, and Matthew E. Taylor. "Providing Uncertainty-Based Advice for Deep Reinforcement Learning Agents (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 10 (April 3, 2020): 13913–14. http://dx.doi.org/10.1609/aaai.v34i10.7229.

Full text

Abstract:

The sample-complexity of Reinforcement Learning (RL) techniques still represents a challenge for scaling up RL to unsolved domains. One way to alleviate this problem is to leverage samples from the policy of a demonstrator to learn faster. However, advice is normally limited, hence advice should ideally be directed to states where the agent is uncertain on the best action to be applied. In this work, we propose Requesting Confidence-Moderated Policy advice (RCMP), an action-advising framework where the agent asks for advice when its uncertainty is high. We describe a technique to estimate the agent uncertainty with minor modifications in standard value-based RL methods. RCMP is shown to perform better than several baselines in the Atari Pong domain.

APA, Harvard, Vancouver, ISO, and other styles

25

Wang, Chun, and Jiquan Ma. "Uncertainty-Supervised Super-Resolution Deep Learning Network in Diffusion MRI." Highlights in Science, Engineering and Technology 45 (April 18, 2023): 7–10. http://dx.doi.org/10.54097/hset.v45i.7288.

Full text

Abstract:

The research of uncertainty has shown great potential in the field of medical image processing. However, most of the research in the field of medical image is aimed at quantifying uncertainty. In this paper, we introduce an uncertainty supervised learning method. Specifically, we integrate the dropout variable reference and heterostatic noise model to estimate uncertainty and then guide super-resolution processing. Finally, we evaluate the enhancement effect of uncertainty supervised learning on super-resolution processing under the demonstration of DIQT model.

APA, Harvard, Vancouver, ISO, and other styles

26

Feng, Zhiyuan, Kai Qi, Bin Shi, Hao Mei, Qinghua Zheng, and Hua Wei. "Deep evidential learning in diffusion convolutional recurrent neural network." Electronic Research Archive 31, no. 4 (2023): 2252–64. http://dx.doi.org/10.3934/era.2023115.

Full text

Abstract:

<abstract><p>Graph neural networks (GNNs) is applied successfully in many graph tasks, but there still exists a limitation that many of GNNs model do not consider uncertainty quantification of its output predictions. For uncertainty quantification, there are mainly two types of methods which are frequentist and Bayesian. But both methods need to sampling to gradually approximate the real distribution, in contrast, evidential deep learning formulates learning as an evidence acquisition process, which could get uncertainty quantification by placing evidential priors over the original Gaussian likelihood function and training the NN to infer the hyperparameters of the evidential distribution without sampling. So evidential deep learning (EDL) has its own advantage in measuring uncertainty. We apply it with diffusion convolutional recurrent neural network (DCRNN), and do the experiment in spatiotemporal forecasting task in a real-world traffic dataset. And we choose mean interval scores (MIS), a good metric for uncertainty quantification. We summarized the advantages of each method.</p></abstract>

APA, Harvard, Vancouver, ISO, and other styles

27

Chaudhary, Priyanka, João P. Leitão, Tabea Donauer, Stefano D’Aronco, Nathanaël Perraudin, Guillaume Obozinski, Fernando Perez-Cruz, Konrad Schindler, Jan Dirk Wegner, and Stefania Russo. "Flood Uncertainty Estimation Using Deep Ensembles." Water 14, no. 19 (September 22, 2022): 2980. http://dx.doi.org/10.3390/w14192980.

Full text

Abstract:

We propose a probabilistic deep learning approach for the prediction of maximum water depth hazard maps at high spatial resolutions, which assigns well-calibrated uncertainty estimates to every predicted water depth. Efficient, accurate, and trustworthy methods for urban flood management have become increasingly important due to higher rainfall intensity caused by climate change, the expansion of cities, and changes in land use. While physically based flood models can provide reliable forecasts for water depth at every location of a catchment, their high computational burden is hindering their application to large urban areas at high spatial resolution. While deep learning models have been used to address this issue, a disadvantage is that they are often perceived as “black-box” models and are overconfident about their predictions, therefore decreasing their reliability. Our deep learning model learns the underlying phenomena a priori from simulated hydrodynamic data, obviating the need for manual parameter setting for every new rainfall event at test time. The only inputs needed at the test time are a rainfall forecast and parameters of the terrain such as a digital elevation model to predict the maximum water depth with uncertainty estimates for complete rainfall events. We validate the accuracy and generalisation capabilities of our approach through experiments on a dataset consisting of catchments within Switzerland and Portugal and 18 rainfall patterns. Our method produces flood hazard maps at 1 m resolution and achieves mean absolute errors as low as 21 cm for extreme flood cases with water above 1 m. Most importantly, we demonstrate that our approach is able to provide an uncertainty estimate for every water depth within the predicted hazard map, thus increasing the model’s trustworthiness during flooding events.

APA, Harvard, Vancouver, ISO, and other styles

28

Li, Xingjian, Pengkun Yang, Yangcheng Gu, Xueying Zhan, Tianyang Wang, Min Xu, and Chengzhong Xu. "Deep Active Learning with Noise Stability." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 12 (March 24, 2024): 13655–63. http://dx.doi.org/10.1609/aaai.v38i12.29270.

Full text

Abstract:

Uncertainty estimation for unlabeled data is crucial to active learning. With a deep neural network employed as the backbone model, the data selection process is highly challenging due to the potential over-confidence of the model inference. Existing methods resort to special learning fashions (e.g. adversarial) or auxiliary models to address this challenge. This tends to result in complex and inefficient pipelines, which would render the methods impractical. In this work, we propose a novel algorithm that leverages noise stability to estimate data uncertainty. The key idea is to measure the output derivation from the original observation when the model parameters are randomly perturbed by noise. We provide theoretical analyses by leveraging the small Gaussian noise theory and demonstrate that our method favors a subset with large and diverse gradients. Our method is generally applicable in various tasks, including computer vision, natural language processing, and structural data analysis. It achieves competitive performance compared against state-of-the-art active learning baselines.

APA, Harvard, Vancouver, ISO, and other styles

29

Hong, Ming, Jianzhuang Liu, Cuihua Li, and Yanyun Qu. "Uncertainty-Driven Dehazing Network." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 1 (June 28, 2022): 906–13. http://dx.doi.org/10.1609/aaai.v36i1.19973.

Full text

Abstract:

Deep learning has made remarkable achievements for single image haze removal. However, existing deep dehazing models only give deterministic results without discussing the uncertainty of them. There exist two types of uncertainty in the dehazing models: aleatoric uncertainty that comes from noise inherent in the observations and epistemic uncertainty that accounts for uncertainty in the model. In this paper, we propose a novel uncertainty-driven dehazing network (UDN) that improves the dehazing results by exploiting the relationship between the uncertain and confident representations. We first introduce an Uncertainty Estimation Block (UEB) to predict the aleatoric and epistemic uncertainty together. Then, we propose an Uncertainty-aware Feature Modulation (UFM) block to adaptively enhance the learned features. UFM predicts a convolution kernel and channel-wise modulation cofficients conitioned on the uncertainty weighted representation. Moreover, we develop an uncertainty-driven self-distillation loss to improve the uncertain representation by transferring the knowledge from the confident one. Extensive experimental results on synthetic datasets and real-world images show that UDN achieves significant quantitative and qualitative improvements, outperforming the state-of-the-arts.

APA, Harvard, Vancouver, ISO, and other styles

30

Kompa, Benjamin, Jasper Snoek, and Andrew L. Beam. "Empirical Frequentist Coverage of Deep Learning Uncertainty Quantification Procedures." Entropy 23, no. 12 (November 30, 2021): 1608. http://dx.doi.org/10.3390/e23121608.

Full text

Abstract:

Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings. Currently, the quality of a model’s uncertainty is evaluated using point-prediction metrics, such as the negative log-likelihood (NLL), expected calibration error (ECE) or the Brier score on held-out data. Marginal coverage of prediction intervals or sets, a well-known concept in the statistical literature, is an intuitive alternative to these metrics but has yet to be systematically studied for many popular uncertainty quantification techniques for deep learning models. With marginal coverage and the complementary notion of the width of a prediction interval, downstream users of deployed machine learning models can better understand uncertainty quantification both on a global dataset level and on a per-sample basis. In this study, we provide the first large-scale evaluation of the empirical frequentist coverage properties of well-known uncertainty quantification techniques on a suite of regression and classification tasks. We find that, in general, some methods do achieve desirable coverage properties on in distribution samples, but that coverage is not maintained on out-of-distribution data. Our results demonstrate the failings of current uncertainty quantification techniques as dataset shift increases and reinforce coverage as an important metric in developing models for real-world applications.

APA, Harvard, Vancouver, ISO, and other styles

31

Yu, Yang, Danruo Deng, Furui Liu, Qi Dou, Yueming Jin, Guangyong Chen, and Pheng Ann Heng. "ANEDL: Adaptive Negative Evidential Deep Learning for Open-Set Semi-supervised Learning." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 15 (March 24, 2024): 16587–95. http://dx.doi.org/10.1609/aaai.v38i15.29597.

Full text

Abstract:

Semi-supervised learning (SSL) methods assume that labeled data, unlabeled data and test data are from the same distribution. Open-set semi-supervised learning (Open-set SSL) con- siders a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers). Most previous works focused on out- lier detection via binary classifiers, which suffer from insufficient scalability and inability to distinguish different types of uncertainty. In this paper, we propose a novel framework, Adaptive Negative Evidential Deep Learning (ANEDL) to tackle these limitations. Concretely, we first introduce evidential deep learning (EDL) as an outlier detector to quantify different types of uncertainty, and design different uncertainty metrics for self-training and inference. Furthermore, we propose a novel adaptive negative optimization strategy, making EDL more tailored to the unlabeled dataset containing both inliers and outliers. As demonstrated empirically, our proposed method outperforms existing state-of-the-art methods across four datasets.

APA, Harvard, Vancouver, ISO, and other styles

32

Klotz, Daniel, Frederik Kratzert, Martin Gauch, Alden Keefe Sampson, Johannes Brandstetter, Günter Klambauer, Sepp Hochreiter, and Grey Nearing. "Uncertainty estimation with deep learning for rainfall–runoff modeling." Hydrology and Earth System Sciences 26, no. 6 (March 31, 2022): 1673–93. http://dx.doi.org/10.5194/hess-26-1673-2022.

Full text

Abstract:

Abstract. Deep learning is becoming an increasingly important way to produce accurate hydrological predictions across a wide range of spatial and temporal scales. Uncertainty estimations are critical for actionable hydrological prediction, and while standardized community benchmarks are becoming an increasingly important part of hydrological model development and research, similar tools for benchmarking uncertainty estimation are lacking. This contribution demonstrates that accurate uncertainty predictions can be obtained with deep learning. We establish an uncertainty estimation benchmarking procedure and present four deep learning baselines. Three baselines are based on mixture density networks, and one is based on Monte Carlo dropout. The results indicate that these approaches constitute strong baselines, especially the former ones. Additionally, we provide a post hoc model analysis to put forward some qualitative understanding of the resulting models. The analysis extends the notion of performance and shows that the model learns nuanced behaviors to account for different situations.

APA, Harvard, Vancouver, ISO, and other styles

33

Lv, Xiaoming, Fajie Duan, Jia-Jia Jiang, Xiao Fu, and Lin Gan. "Deep Active Learning for Surface Defect Detection." Sensors 20, no. 6 (March 16, 2020): 1650. http://dx.doi.org/10.3390/s20061650.

Full text

Abstract:

Most of the current object detection approaches deliver competitive results with an assumption that a large number of labeled data are generally available and can be fed into a deep network at once. However, due to expensive labeling efforts, it is difficult to deploy the object detection systems into more complex and challenging real-world environments, especially for defect detection in real industries. In order to reduce the labeling efforts, this study proposes an active learning framework for defect detection. First, an Uncertainty Sampling is proposed to produce the candidate list for annotation. Uncertain images can provide more informative knowledge for the learning process. Then, an Average Margin method is designed to set the sampling scale for each defect category. In addition, an iterative pattern of training and selection is adopted to train an effective detection model. Extensive experiments demonstrate that the proposed method can render the required performance with fewer labeled data.

APA, Harvard, Vancouver, ISO, and other styles

34

Bi, Wei, Wenhua Chen, and Jun Pan. "Multidisciplinary Reliability Design Considering Hybrid Uncertainty Incorporating Deep Learning." Wireless Communications and Mobile Computing 2022 (November 18, 2022): 1–11. http://dx.doi.org/10.1155/2022/5846684.

Full text

Abstract:

Multidisciplinary reliability design optimization is considered an effective method for solving complex product design optimization problems under the influence of uncertainty factors; however, the high computational cost seriously affects its application in practice. As an important part of multidisciplinary reliability design optimization, multidisciplinary reliability analysis plays a direct leading role in its computational efficiency. At present, multidisciplinary reliability analysis under mixed uncertainty is still nested or sequential execution mode, which leads to the problem of poor disciplinary autonomy and inefficiency in the reliability analysis of complex products. To this end, a multidisciplinary reliability assessment method integrating deep neural networks and probabilistic computational models under mixed uncertainty is proposed for the problem of multidisciplinary reliability analysis under mixed uncertainty. The method considers the stochastic-interval-fuzzy uncertainty, decouples the nested multidisciplinary probability analysis, multidisciplinary likelihood analysis, and multidisciplinary interval analysis, uses deep neural networks to extract subdisciplinary high-dimensional features, and fuses them with probabilistic computational models. Moreover, the whole system is divided into several independent subsystems, then the collected reliability data are classified, and the fault data are attributed to each subsystem. Meanwhile, the environmental conditions of the system are considered, and the corresponding environmental factors are added as input neurons along with each subsystem. In this paper, the effectiveness of the proposed method is verified on numerical calculations and real inverter power failure data.

APA, Harvard, Vancouver, ISO, and other styles

35

Cifci, Mehmet Akif. "A Deep Learning-Based Framework for Uncertainty Quantification in Medical Imaging Using the DropWeak Technique: An Empirical Study with Baresnet." Diagnostics 13, no. 4 (February 20, 2023): 800. http://dx.doi.org/10.3390/diagnostics13040800.

Full text

Abstract:

Lung cancer is a leading cause of cancer-related deaths globally. Early detection is crucial for improving patient survival rates. Deep learning (DL) has shown promise in the medical field, but its accuracy must be evaluated, particularly in the context of lung cancer classification. In this study, we conducted uncertainty analysis on various frequently used DL architectures, including Baresnet, to assess the uncertainties in the classification results. This study focuses on the use of deep learning for the classification of lung cancer, which is a critical aspect of improving patient survival rates. The study evaluates the accuracy of various deep learning architectures, including Baresnet, and incorporates uncertainty quantification to assess the level of uncertainty in the classification results. The study presents a novel automatic tumor classification system for lung cancer based on CT images, which achieves a classification accuracy of 97.19% with an uncertainty quantification. The results demonstrate the potential of deep learning in lung cancer classification and highlight the importance of uncertainty quantification in improving the accuracy of classification results. This study’s novelty lies in the incorporation of uncertainty quantification in deep learning for lung cancer classification, which can lead to more reliable and accurate diagnoses in clinical settings.

APA, Harvard, Vancouver, ISO, and other styles

36

Kim, Mingyu, and Donghyun Lee. "Why Uncertainty in Deep Learning for Traffic Flow Prediction Is Needed." Sustainability 15, no. 23 (November 22, 2023): 16204. http://dx.doi.org/10.3390/su152316204.

Full text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

37

Maged, Ahmed, and Min Xie. "Uncertainty utilization in fault detection using Bayesian deep learning." Journal of Manufacturing Systems 64 (July 2022): 316–29. http://dx.doi.org/10.1016/j.jmsy.2022.07.002.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Feng, Shijie, Chao Zuo, Yan Hu, Yixuan Li, and Qian Chen. "Deep-learning-based fringe-pattern analysis with uncertainty estimation." Optica 8, no. 12 (November 23, 2021): 1507. http://dx.doi.org/10.1364/optica.434311.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Loquercio, Antonio, Mattia Segu, and Davide Scaramuzza. "A General Framework for Uncertainty Estimation in Deep Learning." IEEE Robotics and Automation Letters 5, no. 2 (April 2020): 3153–60. http://dx.doi.org/10.1109/lra.2020.2974682.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Qin, Yu, Zhiwen Liu, Chenghao Liu, Yuxing Li, Xiangzhu Zeng, and Chuyang Ye. "Super-Resolved q-Space deep learning with uncertainty quantification." Medical Image Analysis 67 (January 2021): 101885. http://dx.doi.org/10.1016/j.media.2020.101885.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Peng, Weiwen, Zhi-Sheng Ye, and Nan Chen. "Bayesian Deep-Learning-Based Health Prognostics Toward Prognostics Uncertainty." IEEE Transactions on Industrial Electronics 67, no. 3 (March 2020): 2283–93. http://dx.doi.org/10.1109/tie.2019.2907440.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Xue, Yujia, Shiyi Cheng, Yunzhe Li, and Lei Tian. "Reliable deep-learning-based phase imaging with uncertainty quantification." Optica 6, no. 5 (May 7, 2019): 618. http://dx.doi.org/10.1364/optica.6.000618.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Abdullah, Abdullah A., Masoud M. Hassan, and Yaseen T. Mustafa. "Uncertainty Quantification for MLP-Mixer Using Bayesian Deep Learning." Applied Sciences 13, no. 7 (April 3, 2023): 4547. http://dx.doi.org/10.3390/app13074547.

Full text

Abstract:

Convolutional neural networks (CNNs) have become a popular choice for various image classification applications. However, the multi-layer perceptron mixer (MLP-Mixer) architecture has been proposed as a promising alternative, particularly for large datasets. Despite its advantages in handling large datasets and models, MLP-Mixer models have limitations when dealing with small datasets. This study aimed to quantify and evaluate the uncertainty associated with MLP-Mixer models for small datasets using Bayesian deep learning (BDL) methods to quantify uncertainty and compare the results to existing CNN models. In particular, we examined the use of variational inference and Monte Carlo dropout methods. The results indicated that BDL can improve the performance of MLP-Mixer models by 9.2 to 17.4% in term of accuracy across different mixer models. On the other hand, the results suggest that CNN models tend to have limited improvement or even decreased performance in some cases when using BDL. These findings suggest that BDL is a promising approach to improve the performance of MLP-Mixer models, especially for small datasets.

APA, Harvard, Vancouver, ISO, and other styles

44

Habibpour, Maryam, Hassan Gharoun, Mohammadreza Mehdipour, AmirReza Tajally, Hamzeh Asgharnezhad, Afshar Shamsi, Abbas Khosravi, and Saeid Nahavandi. "Uncertainty-aware credit card fraud detection using deep learning." Engineering Applications of Artificial Intelligence 123 (August 2023): 106248. http://dx.doi.org/10.1016/j.engappai.2023.106248.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Das, Neha, Jonas Umlauft, Armin Lederer, Alexandre Capone, Thomas Beckers, and Sandra Hirche. "Deep Learning based Uncertainty Decomposition for Real-time Control." IFAC-PapersOnLine 56, no. 2 (2023): 847–53. http://dx.doi.org/10.1016/j.ifacol.2023.10.1671.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Koh, D., A. Mishra, and K. Terao. "Deep neural network uncertainty quantification for LArTPC reconstruction." Journal of Instrumentation 18, no. 12 (December 1, 2023): P12013. http://dx.doi.org/10.1088/1748-0221/18/12/p12013.

Full text

Abstract:

Abstract We evaluate uncertainty quantification (UQ) methods for deep learning applied to liquid argon time projection chamber (LArTPC) physics analysis tasks. As deep learning applications enter widespread usage among physics data analysis, neural networks with reliable estimates of prediction uncertainty and robust performance against overconfidence and out-of-distribution (OOD) samples are critical for their full deployment in analyzing experimental data. While numerous UQ methods have been tested on simple datasets, performance evaluations for more complex tasks and datasets are scarce. We assess the application of selected deep learning UQ methods on the task of particle classification using the PiLArNet [1] monte carlo 3D LArTPC point cloud dataset. We observe that UQ methods not only allow for better rejection of prediction mistakes and OOD detection, but also generally achieve higher overall accuracy across different task settings. We assess the precision of uncertainty quantification using different evaluation metrics, such as distributional separation of prediction entropy across correctly and incorrectly identified samples, receiver operating characteristic curves (ROCs), and expected calibration error from observed empirical accuracy. We conclude that ensembling methods can obtain well calibrated classification probabilities and generally perform better than other existing methods in deep learning UQ literature.

APA, Harvard, Vancouver, ISO, and other styles

47

Murad, Abdulmajid, Frank Alexander Kraemer, Kerstin Bach, and Gavin Taylor. "Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting." Sensors 21, no. 23 (November 30, 2021): 8009. http://dx.doi.org/10.3390/s21238009.

Full text

Abstract:

Data-driven forecasts of air quality have recently achieved more accurate short-term predictions. However, despite their success, most of the current data-driven solutions lack proper quantifications of model uncertainty that communicate how much to trust the forecasts. Recently, several practical tools to estimate uncertainty have been developed in probabilistic deep learning. However, there have not been empirical applications and extensive comparisons of these tools in the domain of air quality forecasts. Therefore, this work applies state-of-the-art techniques of uncertainty quantification in a real-world setting of air quality forecasts. Through extensive experiments, we describe training probabilistic models and evaluate their predictive uncertainties based on empirical performance, reliability of confidence estimate, and practical applicability. We also propose improving these models using “free” adversarial training and exploiting temporal and spatial correlation inherent in air quality data. Our experiments demonstrate that the proposed models perform better than previous works in quantifying uncertainty in data-driven air quality forecasts. Overall, Bayesian neural networks provide a more reliable uncertainty estimate but can be challenging to implement and scale. Other scalable methods, such as deep ensemble, Monte Carlo (MC) dropout, and stochastic weight averaging-Gaussian (SWAG), can perform well if applied correctly but with different tradeoffs and slight variations in performance metrics. Finally, our results show the practical impact of uncertainty estimation and demonstrate that, indeed, probabilistic models are more suitable for making informed decisions.

APA, Harvard, Vancouver, ISO, and other styles

48

Aldhahi, Waleed, and Sanghoon Sull. "Uncertain-CAM: Uncertainty-Based Ensemble Machine Voting for Improved COVID-19 CXR Classification and Explainability." Diagnostics 13, no. 3 (January 26, 2023): 441. http://dx.doi.org/10.3390/diagnostics13030441.

Full text

Abstract:

The ongoing coronavirus disease 2019 (COVID-19) pandemic has had a significant impact on patients and healthcare systems across the world. Distinguishing non-COVID-19 patients from COVID-19 patients at the lowest possible cost and in the earliest stages of the disease is a major issue. Additionally, the implementation of explainable deep learning decisions is another issue, especially in critical fields such as medicine. The study presents a method to train deep learning models and apply an uncertainty-based ensemble voting policy to achieve 99% accuracy in classifying COVID-19 chest X-rays from normal and pneumonia-related infections. We further present a training scheme that integrates the cyclic cosine annealing approach with cross-validation and uncertainty quantification that is measured using prediction interval coverage probability (PICP) as final ensemble voting weights. We also propose the Uncertain-CAM technique, which improves deep learning explainability and provides a more reliable COVID-19 classification system. We introduce a new image processing technique to measure the explainability based on ground-truth, and we compared it with the widely adopted Grad-CAM method.

APA, Harvard, Vancouver, ISO, and other styles

49

Ji, Ying, Jianhui Wang, Jiacan Xu, Xiaoke Fang, and Huaguang Zhang. "Real-Time Energy Management of a Microgrid Using Deep Reinforcement Learning." Energies 12, no. 12 (June 15, 2019): 2291. http://dx.doi.org/10.3390/en12122291.

Full text

Abstract:

Driven by the recent advances and applications of smart-grid technologies, our electric power grid is undergoing radical modernization. Microgrid (MG) plays an important role in the course of modernization by providing a flexible way to integrate distributed renewable energy resources (RES) into the power grid. However, distributed RES, such as solar and wind, can be highly intermittent and stochastic. These uncertain resources combined with load demand result in random variations in both the supply and the demand sides, which make it difficult to effectively operate a MG. Focusing on this problem, this paper proposed a novel energy management approach for real-time scheduling of an MG considering the uncertainty of the load demand, renewable energy, and electricity price. Unlike the conventional model-based approaches requiring a predictor to estimate the uncertainty, the proposed solution is learning-based and does not require an explicit model of the uncertainty. Specifically, the MG energy management is modeled as a Markov Decision Process (MDP) with an objective of minimizing the daily operating cost. A deep reinforcement learning (DRL) approach is developed to solve the MDP. In the DRL approach, a deep feedforward neural network is designed to approximate the optimal action-value function, and the deep Q-network (DQN) algorithm is used to train the neural network. The proposed approach takes the state of the MG as inputs, and outputs directly the real-time generation schedules. Finally, using real power-grid data from the California Independent System Operator (CAISO), case studies are carried out to demonstrate the effectiveness of the proposed approach.

APA, Harvard, Vancouver, ISO, and other styles

50

Ji, Ying, Jianhui Wang, Jiacan Xu, and Donglin Li. "Data-Driven Online Energy Scheduling of a Microgrid Based on Deep Reinforcement Learning." Energies 14, no. 8 (April 10, 2021): 2120. http://dx.doi.org/10.3390/en14082120.

Full text

Abstract:

The proliferation of distributed renewable energy resources (RESs) poses major challenges to the operation of microgrids due to uncertainty. Traditional online scheduling approaches relying on accurate forecasts become difficult to implement due to the increase of uncertain RESs. Although several data-driven methods have been proposed recently to overcome the challenge, they generally suffer from a scalability issue due to the limited ability to optimize high-dimensional continuous control variables. To address these issues, we propose a data-driven online scheduling method for microgrid energy optimization based on continuous-control deep reinforcement learning (DRL). We formulate the online scheduling problem as a Markov decision process (MDP). The objective is to minimize the operating cost of the microgrid considering the uncertainty of RESs generation, load demand, and electricity prices. To learn the optimal scheduling strategy, a Gated Recurrent Unit (GRU)-based network is designed to extract temporal features of uncertainty and generate the optimal scheduling decisions in an end-to-end manner. To optimize the policy with high-dimensional and continuous actions, proximal policy optimization (PPO) is employed to train the neural network-based policy in a data-driven fashion. The proposed method does not require any forecasting information on the uncertainty or a prior knowledge of the physical model of the microgrid. Simulation results using realistic power system data of California Independent System Operator (CAISO) demonstrate the effectiveness of the proposed method.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Deep learning with uncertainty'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles