3 citations · 3 across the 1 of their papers we have counts for
3 papers
cs.LG2020
Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning
Andreas Kirsch, Clare Lyle, Yarin Gal
The Information Bottleneck principle offers both a mechanism to explain how deep neural networks train and generalize, as well as a regularized objective with which to train models…
cs.LG2019
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
Andreas Kirsch, Joost van Amersfoort, Yarin Gal
We develop BatchBALD, a tractable approximation to the mutual information between a batch of points and model parameters, which we use as an acquisition function to select multiple…
cs.LG2017★ 3 cited
MDP environments for the OpenAI Gym
Andreas Kirsch
The OpenAI Gym provides researchers and enthusiasts with simple to use environments for reinforcement learning. Even the simplest environment have a level of complexity that can ob…