Search Results for author: Jiri Navratil

Found 7 papers, 2 papers with code

Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI

1 code implementation2 Jun 2021 Soumya Ghosh, Q. Vera Liao, Karthikeyan Natesan Ramamurthy, Jiri Navratil, Prasanna Sattigeri, Kush R. Varshney, Yunfeng Zhang

In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models.


Uncertainty Characteristics Curves: A Systematic Assessment of Prediction Intervals

1 code implementation1 Jun 2021 Jiri Navratil, Benjamin Elder, Matthew Arnold, Soumya Ghosh, Prasanna Sattigeri

Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI.

Prediction Intervals

Learning Prediction Intervals for Model Performance

no code implementations15 Dec 2020 Benjamin Elder, Matthew Arnold, Anupama Murthi, Jiri Navratil

We address this core problem of performance prediction uncertainty with a method to compute prediction intervals for model performance.

Prediction Intervals Transfer Learning

Uncertainty Prediction for Deep Sequential Regression Using Meta Models

no code implementations2 Jul 2020 Jiri Navratil, Matthew Arnold, Benjamin Elder

Generating high quality uncertainty estimates for sequential regression, particularly deep recurrent networks, remains a challenging and open problem.

Towards Automating the AI Operations Lifecycle

no code implementations28 Mar 2020 Matthew Arnold, Jeffrey Boston, Michael Desmond, Evelyn Duesterwald, Benjamin Elder, Anupama Murthi, Jiri Navratil, Darrell Reimer

Today's AI deployments often require significant human involvement and skill in the operational stages of the model lifecycle, including pre-release testing, monitoring, problem diagnosis and model improvements.

Accelerating Physics-Based Simulations Using Neural Network Proxies: An Application in Oil Reservoir Modeling

no code implementations23 May 2019 Jiri Navratil, Alan King, Jesus Rios, Georgios Kollias, Ruben Torrado, Andres Codas

We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirs--by three orders of magnitude--compared to industry-strength physics-based PDE solvers.

Cannot find the paper you are looking for? You can Submit a new open access paper.