… Fackler: oliver.fackler@med.uni-heidelberg.de; or Robert Grosse: robert.grosse@pharma.uni-heidelberg.de
© 2008 Fackler and Grosse This article is distributed under the terms of an …

Formins constitute a diverse protein family present in all eukaryotes examined. They are
defined by the presence of a formin homology 2 (FH2) domain, which possesses intrinsic and …

The invasion of cancer cells into the surrounding tissue is a prerequisite and initial step in
metastasis, which is the leading cause of death from cancer. Invasive cell migration requires …

… hllee@cs.stanford.edu Roger Grosse … (1989) and Grosse et al. (2007), we learn feature
detectors which are shared among all locations in an image, because features which capture …

The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative
model pairing a top-down generative network with a bottom-up recognition network which …

We decompose the evidence lower bound to show the existence of a term measuring the
total correlation between latent variables. We use this to motivate the beta-TCVAE (Total …

The causative agent of the coronavirus disease 2019 (COVID-19) pandemic, severe acute
respiratory syndrome coronavirus 2 (SARS-CoV-2), has infected millions and killed hundreds …

Imaging of collectively invading cocultures of carcinoma cells and stromal fibroblasts reveals
that the leading cell is always a fibroblast and that carcinoma cells move within tracks in the …

We propose an efficient method for approximating natural gradient descent in neural networks
which we call Kronecker-factored Approximate Curvature (K-FAC). K-FAC is based on an …

In this work, we propose to apply trust region optimization to deep reinforcement learning
using a recently proposed Kronecker-factored approximation to the curvature. We extend the …