31,685 Hits in 3.3 sec

Towards Principled Uncertainty Estimation for Deep Neural Networks [article]

Richard Harang, Ethan M. Rudd
2019 arXiv   pre-print
network topology to yield efficient per-sample uncertainty estimation in a detection context.  ...  When the cost of misclassifying a sample is high, it is useful to have an accurate estimate of uncertainty in the prediction for that sample.  ...  In this paper, however, we are interested in deep neural networks as generic estimators.  ... 
arXiv:1810.12278v2 fatcat:ianln5p6tvhhnc2x6lhqegfhb4

Building Trust in Deep Learning System towards Automated Disease Detection

Zhan Wei Lim, Mong Li Lee, Wynne Hsu, Tien Yin Wong
We propose to use uncertainty estimates of the deep learning system's prediction to know when to accept or to disregard its prediction.  ...  We evaluate the effectiveness of using such estimates in a real-life application for the screening of diabetic retinopathy.  ...  We thank the anonymous reviewers for their feedback.  ... 
doi:10.1609/aaai.v33i01.33019516 fatcat:q5yzexds6vfyrioxey7pj2z6ee

Deep and Confident Prediction for Time Series at Uber

Lingxue Zhu, Nikolay Laptev
2017 2017 IEEE International Conference on Data Mining Workshops (ICDMW)  
Motivated by the recent resurgence of Long Short Term Memory networks, we propose a novel end-to-end Bayesian deep model that provides time series prediction along with uncertainty estimation.  ...  Reliable uncertainty estimation for time series prediction is critical in many fields, including physics, biology, and manufacturing.  ...  Recently, Bayesian neural networks (BNNs) have garnered increasing attention as a principled framework to provide uncertainty estimation for deep models.  ... 
doi:10.1109/icdmw.2017.19 dblp:conf/icdm/ZhuL17 fatcat:4ddoyrrqbjhtxdh3p4wk3gyt2a

Out-of-Distribution Robustness with Deep Recursive Filters [article]

Kapil D. Katyal, I-Jeng Wang, Gregory D. Hager
2021 arXiv   pre-print
Here, we describe an approach that combines the expressiveness of deep neural networks with principled approaches to uncertainty estimation found in recursive filters.  ...  A critical component of state and uncertainty estimation for robot navigation is to perform robustly under out-of-distribution noise.  ...  ACKNOWLEDGMENTS This work was funded by the JHU Institute for Assured Autonomy and the JHU/APL Independent Research and Development Program.  ... 
arXiv:2104.02799v1 fatcat:zidoflbz6bcjdio5sh33tb762i

On the Validity of Bayesian Neural Networks for Uncertainty Estimation [article]

John Mitros, Brian Mac Namee
2019 arXiv   pre-print
This paper describes a study that empirically evaluates and compares Bayesian Neural Networks to their equivalent point estimate Deep Neural Networks to quantify the predictive uncertainty induced by their  ...  In this study, we evaluated and compared three point estimate deep neural networks against comparable Bayesian neural network alternatives using two well-known benchmark image classification datasets (  ...  Bayesian deep neural networks provide a principled and viable alternative that allows the models to be informed about the uncertainty in their parameters and at the same time exhibits a lower degree of  ... 
arXiv:1912.01530v2 fatcat:oxbzzj4vibb37pbme6o66aff5y

Misclassification Risk and Uncertainty Quantification in Deep Classifiers

Murat Sensoy, Maryam Saleki, Simon Julier, Reyhan Aydogan, John Reid
2021 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)  
We combine these two approaches in a principled way.  ...  While doing this, we extend evidential deep learning with pignistic probabilities, which are used to quantify uncertainty of classification predictions and model rational decision making under uncertainty  ...  Army Research Laboratory for its support under grant W911NF-16-2-0173.  ... 
doi:10.1109/wacv48630.2021.00253 fatcat:uzi2qsdlsjhi5k6jyreet5vi64

The Hidden Uncertainty in a Neural Networks Activations [article]

Janis Postels, Hermann Blum, Yannick Strümpler, Cesar Cadena, Roland Siegwart, Luc Van Gool, Federico Tombari
2021 arXiv   pre-print
more expensive - methods (e.g. deep ensembles).  ...  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data.  ...  Towards principled uncer- tainty estimation for deep neural networks. arXiv preprint arXiv:1810.12278, 2018. He, K., Zhang, X., Ren, S., and Sun, J. Deep residual learn- ing for image recognition.  ... 
arXiv:2012.03082v2 fatcat:2txmq45dhbaytgoc7vn6dyvwuu

Bayesian Neural Networks for Reversible Steganography [article]

Ching-Chun Chang
2022 arXiv   pre-print
A fundamental pillar of reversible steganography is predictive modelling which can be realised via deep neural networks.  ...  Bayesian neural networks can be regarded as self-aware machinery; that is, a machine that knows its own limitations.  ...  A dual-headed neural network is constructed for estimating uncertainty in an unsupervised manner.  ... 
arXiv:2201.02478v1 fatcat:3sgon3ktundc5pfqqzixdddhxa

Calibrated and Sharp Uncertainties in Deep Learning via Simple Density Estimation [article]

Volodymyr Kuleshov, Shachi Deshpande
2021 arXiv   pre-print
This paper argues for reasoning about uncertainty in terms these properties and proposes simple algorithms for enforcing them in deep learning.  ...  Our methods focus on the strongest notion of calibration--distribution calibration--and enforce it by fitting a low-dimensional density or quantile function with a neural estimator.  ...  We also compare against a popular uncertainty estimation method recently developed specifically for deep learning models: deep ensembles .  ... 
arXiv:2112.07184v1 fatcat:qaw6we4azjcgvg26acudtyazre

Bayesian Neural Networks for Reversible Steganography

Ching-Chun Chang
2022 IEEE Access  
A fundamental pillar of reversible steganography is predictive modelling which can be realised via deep neural networks.  ...  Bayesian neural networks bring a probabilistic perspective to deep learning and can be regarded as self-aware intelligent machinery; that is, a machine that knows its own limitations.  ...  A dual-headed neural network is constructed for estimating uncertainty in an unsupervised manner.  ... 
doi:10.1109/access.2022.3159911 fatcat:gcov63thsfgvtg7or4cfmctruy

A Survey of Uncertainty in Deep Neural Networks [article]

Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, Jongseok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, Muhammad Shahzad, Wen Yang (+2 others)
2022 arXiv   pre-print
For a practical application, we discuss different measures of uncertainty, approaches for the calibration of neural networks and give an overview of existing baselines and implementations.  ...  However, basic neural networks do not deliver certainty estimates or suffer from over or under confidence.  ...  bining principled Bayesian learning for deep neural networks.  ... 
arXiv:2107.03342v3 fatcat:cex5j3xq5fdijjdtdbt2ixralm

Estimating uncertainty in deep learning for reporting confidence to clinicians in medical image segmentation and diseases detection

Biraja Ghoshal, Allan Tucker, Bal Sanghera, Wai Lup Wong
2020 Computational intelligence  
Deep learning (DL), which involves powerful black box predictors, has achieved a remarkable performance in medical image analysis, such as segmentation and classification for diagnosis.  ...  In this article, we propose an uncertainty estimation framework, called MC-DropWeights, to approximate Bayesian inference in DL by imposing a Bernoulli distribution on the incoming or outgoing weights  ...  Estimating uncertainty in deep neural networks is a challenging and yet unsolved problem.  ... 
doi:10.1111/coin.12411 fatcat:i5dzsbkicnaifko2d6jkkbd5sy

Uncertainty-Based Out-of-Distribution Detection in Deep Reinforcement Learning [article]

Andreas Sedlmeier, Thomas Gabor, Thomy Phan, Lenz Belzner, Claudia Linnhoff-Popien
2019 arXiv   pre-print
In a value based reinforcement learning setting, we propose to use uncertainty estimation techniques directly on the agent's value estimating neural network to detect OOD samples.  ...  Although prior work has shown that dropout-based variational inference techniques and bootstrap-based approaches can be used to model epistemic uncertainty, the suitability for detecting OOD samples in  ...  We focus on deep Q-Learning [20] , integrating directly with the agent's value-estimating neural network.  ... 
arXiv:1901.02219v1 fatcat:j6pxwgzknjakdg3hn77ykrv5wq

Epistemic Deep Learning [article]

Shireen Kudukkil Manchingal, Fabio Cuzzolin
2022 arXiv   pre-print
In this paper, we introduce a concept called epistemic deep learning based on the random-set interpretation of belief functions to model epistemic learning in deep neural networks.  ...  We propose a novel random-set convolutional neural network for classification that produces scores for sets of classes by learning set-valued ground truth representations.  ...  Random-set convolutional neural networks Having discussed the principles of epistemic deep learning, we wish to propose a design for a random-set convolutional neural network that can be trained to output  ... 
arXiv:2206.07609v1 fatcat:q7mbcls74jaojlmepkpvevgtuu

Uncertainty-Aware Deep Classifiers Using Generative Models

Murat Sensoy, Lance Kaplan, Federico Cerutti, Maryam Saleki
Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions.  ...  against state-of-the-art approaches including recent Bayesian approaches for neural networks and anomaly detection methods.  ...  Governments are authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon. Also, Dr. Sensoy thanks to ARL for its support  ... 
doi:10.1609/aaai.v34i04.6015 fatcat:v5lveat4e5fxte3w4pvymkpmzi
« Previous Showing results 1 — 15 out of 31,685 results