Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors
نویسندگان
چکیده
منابع مشابه
Auxiliary Deep Generative Models
Deep generative models parameterized by neural networks have recently achieved state-ofthe-art performance in unsupervised and semisupervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave the generative model unchanged but make the variational distribution more expressive. Inspired by the structure...
متن کاملDerivation of Unstructured MIMO Uncertainty Models via Data Matching
A procedure for deriving norm-bounded uncertainty models for MIMO systems is presented. Additive as well as multiplicative input and output uncertainty models with unstructured uncertainty are treated in a unified manner. The models are determined by matching the input-output behavior of an uncertainty model to sets of input-output data obtained, e.g., through system identification. Tight bound...
متن کاملCalibrated Uncertainty
We define a binary relation (qualitative uncertainty assessment (QUA)) to describe a decision-maker’s subjective assessment of likelihoods on a collection of events. To model ambiguity, we permit incompleteness. Our axioms yield a representation according to which A is more likely than B if an only if a capacity, called uncertainty measure (UM) assigns a higher value to A than to B and a higher...
متن کاملImproving Semi-Supervised Learning with Auxiliary Deep Generative Models
Abstract Deep generative models based upon continuous variational distributions parameterized by deep networks give state-of-the-art performance. In this paper we propose a framework for extending the latent representation with extra auxiliary variables in order to make the variational distribution more expressive for semi-supervised learning. By utilizing the stochasticity of the auxiliary var...
متن کاملReducing Uncertainty of Schema Matching via Crowdsourcing
Schema matching is a central challenge for data integration systems. Automated tools are often uncertain about schema matchings they suggest, and this uncertainty is inherent since it arises from the inability of the schema to fully capture the semantics of the represented data. Human common sense can often help. Inspired by the popularity and the success of easily accessible crowdsourcing plat...
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: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2020
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v34i04.6062