English
Related papers

Related papers: Understanding Softmax Confidence and Uncertainty

200 papers

Network diffusion models are used to study disease transmission, information spread, technology adoption, and other socio-economic processes. We show that estimates of these diffusions are highly non-robust to mismeasurement. First, even…

Deep learning (DL) techniques have achieved great success in predictive accuracy in a variety of tasks, but deep neural networks (DNNs) are shown to produce highly overconfident scores for even abnormal samples. Well-defined uncertainty…

Machine Learning · Computer Science 2021-07-26 Yufei Li , Simin Chen , Wei Yang

Most existing methods of Out-of-Domain (OOD) intent classification rely on extensive auxiliary OOD corpora or specific training paradigms. However, they are underdeveloped in the underlying principle that the models should have…

Computation and Language · Computer Science 2024-04-25 Yunhua Zhou , Pengyu Wang , Peiju Liu , Yuxin Wang , Xipeng Qiu

Successful deep neural networks discover salient features of data. We show when and why they fail to learn out-of-distribution (OOD)-relevant representations from an in-distribution (ID) training window. This requires decoupling feature…

Machine Learning · Computer Science 2026-05-14 Leonel Aguilar , Jan Nagler , Christoph Hoelscher , Nino Antulov-Fantulin

The recent success of neural network models has shone light on a rather surprising statistical phenomenon: statistical models that perfectly fit noisy data can generalize well to unseen test data. Understanding this phenomenon of…

Machine Learning · Statistics 2022-09-13 Niladri S. Chatterji , Philip M. Long , Peter L. Bartlett

Even though probabilistic treatments of neural networks have a long history, they have not found widespread use in practice. Sampling approaches are often too slow already for simple networks. The size of the inputs and the depth of typical…

Computer Vision and Pattern Recognition · Computer Science 2018-05-30 Jochen Gast , Stefan Roth

To detect distribution shifts and improve model safety, many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained on in-distribution data. In this paper, we critically…

Machine Learning · Computer Science 2025-07-03 Yucen Lily Li , Daohan Lu , Polina Kirichenko , Shikai Qiu , Tim G. J. Rudner , C. Bayan Bruss , Andrew Gordon Wilson

The inaccuracy of neural network models on inputs that do not stem from the training data distribution is both problematic and at times unrecognized. Model uncertainty estimation can address this issue, where uncertainty estimates are often…

Machine Learning · Computer Science 2020-02-14 Siddhartha Jain , Ge Liu , Jonas Mueller , David Gifford

There has been a growing interest in deep learning-based prognostic and health management (PHM) for building end-to-end maintenance decision support systems, especially due to the rapid development of autonomous systems. However, the low…

Machine Learning · Computer Science 2021-11-02 Taotao Zhou , Enrique Lopez Droguett , Ali Mosleh , Felix T. S. Chan

Out-of-Distribution (OoD) inputs are examples that do not belong to the true underlying distribution of the dataset. Research has shown that deep neural nets make confident mispredictions on OoD inputs. Therefore, it is critical to identify…

Machine Learning · Computer Science 2022-05-10 Deepak Ravikumar , Kaushik Roy

In order to safely deploy Deep Neural Networks (DNNs) within the perception pipelines of real-time decision making systems, there is a need for safeguards that can detect out-of-training-distribution (OoD) inputs both efficiently and…

Machine Learning · Computer Science 2021-02-26 Apoorva Sharma , Navid Azizan , Marco Pavone

One of the challenges for neural networks in real-life applications is the overconfident errors these models make when the data is not from the original training distribution. Addressing this issue is known as Out-of-Distribution (OOD)…

Computer Vision and Pattern Recognition · Computer Science 2024-07-24 Sina Sharifi , Taha Entesari , Bardia Safaei , Vishal M. Patel , Mahyar Fazlyab

We propose a feed-forward inference method applicable to belief and neural networks. In a belief network, the method estimates an approximate factorized posterior of all hidden units given the input. In neural networks the method propagates…

Machine Learning · Statistics 2018-11-02 Alexander Shekhovtsov , Boris Flach , Michal Busta

Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate…

Machine Learning · Computer Science 2019-10-04 Tiago Ramalho , Miguel Miranda

Deep Learning (DL) has made remarkable achievements in computer vision and adopted in safety critical domains such as medical imaging or autonomous drive. Thus, it is necessary to understand the uncertainty of the model to effectively…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Hyekyoung Hwang , Jitae Shin

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine Learning · Statistics 2019-10-29 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Gal Novik

The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer architecture. However, the underlying learning dynamics that…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

Recent work introduced the epinet as a new approach to uncertainty modeling in deep learning. An epinet is a small neural network added to traditional neural networks, which, together, can produce predictive distributions. In particular,…

Machine Learning · Computer Science 2022-07-04 Xiuyuan Lu , Ian Osband , Seyed Mohammad Asghari , Sven Gowal , Vikranth Dwaracherla , Zheng Wen , Benjamin Van Roy

Deep generative models (DGMs) seem a natural fit for detecting out-of-distribution (OOD) inputs, but such models have been shown to assign higher probabilities or densities to OOD images than images from the training distribution. In this…

Machine Learning · Computer Science 2021-07-20 Lily H. Zhang , Mark Goldstein , Rajesh Ranganath

Recently, deep learning has achieved remarkable successes in medical image analysis. Although deep neural networks generate clinically important predictions, they have inherent uncertainty. Such uncertainty is a major barrier to report…

Image and Video Processing · Electrical Eng. & Systems 2022-06-03 Qing Lyu , Christopher T. Whitlow , Ge Wang