Y
Yarin Gal
Researcher at University of Oxford
Publications - 26
Citations - 112
Yarin Gal is an academic researcher from University of Oxford. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 4, co-authored 26 publications receiving 70 citations.
Papers
More filters
Posted ContentDOI
Technology Readiness Levels for Machine Learning Systems.
Alexander Lavin,Ciarán M. Gilligan-Lee,Alessya Visnjic,Siddha Ganju,Dava J. Newman,Sujoy Ganguly,Danny Lange,Atılım Güneş Baydin,Amit Sharma,Adam Gibson,Yarin Gal,Eric P. Xing,Chris A. Mattmann,James Parr +13 more
TL;DR: The Machine Learning Technology Readiness Levels (MLTRL) framework defines a principled process to ensure robust, reliable, and responsible systems while being streamlined for ML workflows, including key distinctions from traditional software engineering.
Posted Content
Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty
TL;DR: In this paper, the authors show that a single softmax neural net with minimal changes can beat the uncertainty predictions of Deep Ensembles and other more complex single forward pass uncertainty approaches.
Posted Content
On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty
TL;DR: The authors constrain the feature extractor to approximately preserve distances through a bi-Lipschitz constraint, resulting in a feature space favorable to deep kernel learning, and obtain a model that demonstrates uncertainty quality outperforming previous DKL and single forward pass uncertainty methods, while maintaining the speed and accuracy of softmax neural networks.
Posted Content
Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression.
TL;DR: The authors proposed a new model that combines a bi-Lipschitz feature extractor with an inducing point approximate Gaussian process to estimate uncertainty in a single forward pass and works on both classification and regression problems.
Journal ArticleDOI
Uncertainty Quantification for Virtual Diagnostic of Particle Accelerators
TL;DR: E ensemble methods and quantile regression neural networks are used to explore different ways of creating and analyzing prediction’s uncertainty on experimental data from the Linac Coherent Light Source at SLAC National Lab.