Reliable classification: Learning classifiers that distinguish aleatoric and epistemic uncertainty
نویسندگان
چکیده
منابع مشابه
Reliable classification: Learning classifiers that distinguish aleatoric and epistemic uncertainty
A proper representation of the uncertainty involved in a prediction is an important prerequisite for the acceptance of machine learning and decision support technology in safety-critical application domains such as medical diagnosis. Despite the existence of various probabilistic approaches in these fields, there is arguably no method that is able to distinguish between two very different sourc...
متن کاملLearning classifiers that perform probabilistic classification under computational resource constraints
Existing online machine learning techniques are often tuned to minimized computational resources, and are not able to utilize further resources when they are available. This is likely to result in sub-optimal learning performance in many online applications where the computational resources available will vary from time to time. This paper analyzes categories of computational resources and defi...
متن کاملDecomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
Bayesian neural networks (BNNs) with latent variables are probabilistic models which can automatically identify complex stochastic patterns in the data. We study in these models a decomposition of predictive uncertainty into its epistemic and aleatoric components. We show how such a decomposition arises naturally in a Bayesian active learning scenario and develop a new objective for reliable re...
متن کاملRobustness-based portfolio optimization under epistemic uncertainty
In this paper, we propose formulations and algorithms for robust portfolio optimization under both aleatory uncertainty (i.e., natural variability) and epistemic uncertainty (i.e., imprecise probabilistic information) arising from interval data. Epistemic uncertainty is represented using two approaches: (1) moment bounding approach and (2) likelihood-based approach. This paper first proposes a ...
متن کاملWhat Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model – uncertainty which can be explained away given enough data. Traditionally it has been difficult to model epistemic uncertainty in computer vision, but with new Bayesian deep learning tools this ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Information Sciences
سال: 2014
ISSN: 0020-0255
DOI: 10.1016/j.ins.2013.07.030