Wind behaviour prediction for protection of infrastructure Predicting and warning extreme wind behaviour to improve public safety and protect key infrastructure
Detecting hazardous physical activity Using human action detection to monitor safety in hazardous or physically demanding situations, such as escalator use and offshore wind turbine work
Statistics and computation Monday 13 Jan 2020 - Tuesday 14 Jan 2020 Time: 10:00 - 17:00 Carola-Bibiane Schönlieb Caroline Uhler Florent Krzakala Francis Bach Garvesh Raskutti Jean-Philippe Vert Lorenzo Rosasco Madeleine Udell Peter Bartlett Rebecca Willett Tamara Broderick Vitaly Feldman
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs Exciting new work on generalization bounds for neural networks (NN) given by Bartlett et... Sanyal, Amartya & Torr, Philip & Dokania, Puneet. (2019). Stable Rank Normalization for Improved Generalization in Neural Networks and GANs.
Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping Consider an unknown smooth function f:[0,1]d→R, and say we are given n noisy mod... M. Cucuringu, H. Tyagi, "Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping", arXiv:1803.03669 (2018), accepted to Journal of Machine Learning Research (JMLR)
Machine learning and dynamical systems How do we analyse dynamical systems on the basis of observed data, rather than attempt to study them analytically?