Albert Zeyer

Artificial Intelligence · 2016–2019

A researcher in the Science corpus: 12 papers; trusts 438 researchers and is trusted by 44 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 284 citations into it; #3,835 of 35,345 by trust here, #4,656 by citations
• Natural Language Processing — 168 citations into it; #1,387 of 5,688 by trust here, #2,106 by citations
• Signal Processing — 128 citations into it; #4,125 of 7,572 by trust here, #3,913 by citations
• Speech & Audio — 102 citations into it; #256 of 1,076 by trust here, #271 by citations
• Model Architectures — 90 citations into it; #1,198 of 2,278 by trust here, #1,572 by citations
• Computer Vision and Pattern Recognition — 77 citations into it; #10,449 of 21,575 by trust here, #11,721 by citations
• Optimization & Training — 41 citations into it
• Large Language Models — 16 citations into it; #396 of 799 by trust here, #648 by citations

Whom Albert Zeyer trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Diederik P. Kingma
2. Alex Graves
3. Yoshua Bengio
4. Geoffrey E. Hinton
5. Dzmitry Bahdanau
6. Ilya Sutskever
7. Jimmy Ba
8. Sepp Hochreiter
9. J. Urgen Schmidhuber
10. Kyunghyun Cho

Who trusts Albert Zeyer overall

1. Kazuki Irie
2. Jinyu Li
3. Ralf Schlüter
4. Hermann Ney
5. Christoph Lüscher
6. Rohit Prabhavalkar
7. Ronan Collobert
8. Awni Y. Hannun
9. Parnia Bahar
10. Gabriel Synnaeve

Papers from Albert Zeyer's perspective

Ordered by how strongly the researchers Albert Zeyer trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
9. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Improved training of end-to-end attention models for speech recognition (2018) — 281 citations
• RWTH ASR Systems for LibriSpeech: Hybrid vs Attention - w/o Data Augmentation (2019) — 240 citations
• Language Modeling with Deep Transformers (2019) — 199 citations
• A Comparison of Transformer and LSTM Encoder Decoder Models for ASR (2019) — 217 citations
• A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition (2016) — 175 citations
• CTC in the Context of Generalized Full-Sum HMM Training (2017) — 43 citations
• RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition (2018) — 96 citations
• Returnn: The RWTH extensible training framework for universal recurrent neural networks (2016) — 79 citations
• A comprehensive analysis on attention models (2019) — 18 citations
• Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems (2019) — 96 citations
• The RWTH/UPB/FORTH System Combination for the 4th CHiME Challenge Evaluation (2016) — 48 citations
• Bidirectional Decoder Networks for Attention-Based End-to-End Offline Handwriting Recognition (2016) — 27 citations