no code implementations • 4 Oct 2023 • 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.
1 code implementation • 1 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.
no code implementations • 15 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.
1 code implementation • 13 Nov 2020 • Jonathan Braden, Clare Burrage, Benjamin Elder, Daniela Saadeh
In this work, we present the numerical code $\varphi$enics, building on the FEniCS library, to solve the full equations of motion from two theories of interest for screening: a model containing high-order derivative operators in the equation of motion and one characterised by nonlinear self-interactions in two coupled scalar fields.
General Relativity and Quantum Cosmology Cosmology and Nongalactic Astrophysics High Energy Physics - Theory
no code implementations • 10 Jul 2020 • Begum Taskazan, Jiri Navratil, Matthew Arnold, Anupama Murthi, Ganesh Venkataraman, Benjamin Elder
Building and maintaining high-quality test sets remains a laborious and expensive task.
no code implementations • 2 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.
no code implementations • 28 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.
no code implementations • 17 Jan 2019 • Atin Sood, Benjamin Elder, Benjamin Herta, Chao Xue, Costas Bekas, A. Cristiano I. Malossi, Debashish Saha, Florian Scheidegger, Ganesh Venkataraman, Gegi Thomas, Giovanni Mariani, Hendrik Strobelt, Horst Samulowitz, Martin Wistuba, Matteo Manica, Mihir Choudhury, Rong Yan, Roxana Istrate, Ruchir Puri, Tejaswini Pedapati
Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice.