Karl Moritz Hermann
Artificial Intelligence · 2013–2018
A researcher in the Science corpus: 21 papers; trusts 1,458 researchers and is trusted by 4,067 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 476 citations into it; #328 of 36,961 by trust here, #437 by citations
- Natural Language Processing — 300 citations into it; #143 of 5,725 by trust here, #127 by citations
- Computer Vision and Pattern Recognition — 159 citations into it; #1,830 of 21,973 by trust here, #769 by citations
- Model Architectures — 72 citations into it; #2,189 of 2,288 by trust here, #360 by citations
- Representation & Self-Supervised Learning — 64 citations into it; #477 of 3,156 by trust here, #940 by citations
- Reinforcement Learning — 50 citations into it
- Language and Linguistics — 42 citations into it; #436 of 3,482 by trust here, #593 by citations
- Evaluation & Benchmarks — 33 citations into it
Whom Karl Moritz Hermann trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard Socher
- Yoshua Bengio
- Geoffrey E. Hinton
- Tomas Mikolov
- Ilya Sutskever
- Alex Graves
- Ronan Collobert
- Diederik P. Kingma
- Yann LeCun
- Alex Krizhevsky
Who trusts Karl Moritz Hermann overall
- Mohit Bansal
- Yoshua Bengio
- Phil Blunsom
- Kyunghyun Cho
- Edward Grefenstette
- Yang Liu
- Jianfeng Gao
- Sebastian Ruder
- Sebastian Gehrmann
- Yi Tay
Papers from Karl Moritz Hermann's perspective
Ordered by how strongly the researchers Karl Moritz Hermann trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Teaching Machines to Read and Comprehend (2015) — 3,880 citations
- Hybrid computing using a neural network with dynamic external memory (2016) — 1,765 citations
- Learning to Transduce with Unbounded Memory (2015) — 305 citations
- Grounded Language Learning in a Simulated 3D World (2017) — 317 citations
- The NarrativeQA Reading Comprehension Challenge (2017) — 1,062 citations
- Reasoning about Entailment with Neural Attention (2015) — 779 citations
- Latent Predictor Networks for Code Generation (2016) — 410 citations
- Learning to Navigate in Cities Without a Map (2018) — 347 citations
- Multilingual Models for Compositional Distributed Semantics (2014) — 319 citations
- Multilingual Distributed Representations without Word Alignment (2013) — 161 citations
- Deep Learning for Answer Sentence Selection (2014) — 421 citations
- Hyperbolic Attention Networks (2018) — 276 citations
- Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input (2018) — 247 citations
- Understanding Grounded Language Learning Agents (2017) — 32 citations
- Semantic Frame Identification with Distributed Word Representations (2014) — 128 citations
- Semantic Parsing with Semi-Supervised Sequential Autoencoders (2016) — 79 citations
- Learning Bilingual Word Representations by Marginalizing Alignments (2014) — 83 citations
- The Role of Syntax in Vector Space Models of Compositional Semantics (2013) — 181 citations
- A Deep Architecture for Semantic Parsing (2014) — 60 citations
- “Not not bad” is not “bad”: A distributional account of negation (2013) — 48 citations