M
Martin Heusel
Researcher at Johnson & Johnson Pharmaceutical Research and Development
Publications - 9
Citations - 9940
Martin Heusel is an academic researcher from Johnson & Johnson Pharmaceutical Research and Development. The author has contributed to research in topics: Stochastic gradient descent & Nash equilibrium. The author has an hindex of 8, co-authored 9 publications receiving 6808 citations. Previous affiliations of Martin Heusel include Johannes Kepler University of Linz.
Papers
More filters
Posted Content
GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium
Martin Heusel,Hubert Ramsauer,Thomas Unterthiner,Bernhard Nessler,Günter Klambauer,Sepp Hochreiter +5 more
TL;DR: In this article, a two time-scale update rule (TTUR) was proposed for training GANs with stochastic gradient descent on arbitrary GAN loss functions, which has an individual learning rate for both the discriminator and the generator.
Proceedings Article
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
TL;DR: In this paper, a two time-scale update rule (TTUR) was proposed for training GANs with stochastic gradient descent on arbitrary GAN loss functions, which has an individual learning rate for both the discriminator and the generator.
Journal ArticleDOI
FABIA: Factor Analysis for Bicluster Acquisition
Sepp Hochreiter,Ulrich Bodenhofer,Martin Heusel,Andreas Mayr,Andreas Mitterecker,Adetayo Kasim,Tatsiana Khamiakova,Suzy Van Sanden,Dan Lin,Willem Talloen,Luc Bijnens,Hinrich W. H. Göhlmann,Ziv Shkedy,Djork-Arné Clevert +13 more
TL;DR: A novel generative approach for biclustering called FABIA: Factor Analysis for Bicluster Acquisition, based on a multiplicative model, which accounts for linear dependencies between gene expression and conditions, and also captures heavy-tailed distributions as observed in real-world transcriptomic data
Speeding up Semantic Segmentation for Autonomous Driving
Michael Treml,Jose A. Arjona-Medina,Thomas Unterthiner,Rupesh Durgesh,Felix Friedmann,Peter Schuberth,Andreas Mayr,Martin Heusel,Markus Hofmarcher,Michael Widrich,Bernhard Nessler,Sepp Hochreiter +11 more
TL;DR: A novel deep network architecture for image segmentation that keeps the high accuracy while being efficient enough for embedded devices is proposed, and achieves higher segmentation accuracy than other networks that are tailored to embedded devices.
Journal ArticleDOI
Fast model-based protein homology detection without alignment
TL;DR: A fast model-based recurrent neural network for protein homology detection, the 'Long Short-Term Memory' (LSTM), which reaches state-of-the-art classification performance but is considerably faster for classification than other approaches with comparable classification performance.