L
Lasse Espeholt
Researcher at Google
Publications - 26
Citations - 8824
Lasse Espeholt is an academic researcher from Google. The author has contributed to research in topics: Reinforcement learning & Football. The author has an hindex of 15, co-authored 24 publications receiving 7039 citations.
Papers
More filters
Proceedings Article
Teaching machines to read and comprehend
Karl Moritz Hermann,Tomáš Kočiský,Edward Grefenstette,Lasse Espeholt,Will Kay,Mustafa Suleyman,Phil Blunsom +6 more
TL;DR: A new methodology is defined that resolves this bottleneck and provides large scale supervised reading comprehension data that allows a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure to be developed.
Proceedings Article
Conditional image generation with PixelCNN decoders
Aaron van den Oord,Nal Kalchbrenner,Oriol Vinyals,Lasse Espeholt,Alex Graves,Koray Kavukcuoglu +5 more
TL;DR: The gated convolutional layers in the proposed model improve the log-likelihood of PixelCNN to match the state-of-the-art performance of PixelRNN on ImageNet, with greatly reduced computational cost.
Posted Content
Conditional Image Generation with PixelCNN Decoders
Aaron van den Oord,Nal Kalchbrenner,Oriol Vinyals,Lasse Espeholt,Alex Graves,Koray Kavukcuoglu +5 more
TL;DR: In this paper, a new image density model based on the PixelCNN architecture is proposed for conditional image generation, which can be conditioned on any vector, including descriptive labels or tags, or latent embeddings created by other networks.
Posted Content
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Lasse Espeholt,Hubert Soyer,Rémi Munos,Karen Simonyan,Volodymyr Mnih,Tom Ward,Yotam Doron,Vlad Firoiu,Tim Harley,Iain Dunning,Shane Legg,Koray Kavukcuoglu +11 more
TL;DR: A new distributed agent IMPALA (Importance Weighted Actor-Learner Architecture) is developed that not only uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation.
Posted Content
Teaching Machines to Read and Comprehend
Karl Moritz Hermann,Tomáš Kočiský,Edward Grefenstette,Lasse Espeholt,Will Kay,Mustafa Suleyman,Phil Blunsom +6 more
TL;DR: This article developed a class of attention-based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure, but this method requires large-scale reading comprehension data.