Matthias Sperber

Artificial Intelligence · 2017–2020

A researcher in the Science corpus: 6 papers; trusts 155 researchers and is trusted by 5 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 96 citations into it; #20,917 of 35,345 by trust here, #14,181 by citations
• Natural Language Processing — 61 citations into it; #3,977 of 5,688 by trust here, #4,601 by citations
• Computer Vision and Pattern Recognition — 36 citations into it
• Model Architectures — 31 citations into it; #2,055 of 2,278 by trust here, #1,665 by citations
• Speech & Audio — 20 citations into it; #974 of 1,076 by trust here, #694 by citations
• Machine Translation — 14 citations into it; #270 of 292 by trust here, #192 by citations
• Optimization & Training — 12 citations into it
• Signal Processing — 10 citations into it; #7,022 of 7,572 by trust here, #3,428 by citations

Whom Matthias Sperber trusts overall

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

1. Diederik P. Kingma
2. Yoshua Bengio
3. Ilya Sutskever
4. Geoffrey E. Hinton
5. Jimmy Ba
6. Dzmitry Bahdanau
7. Alex Graves
8. Alex Krizhevsky
9. Oriol Vinyals
10. Kyunghyun Cho

Who trusts Matthias Sperber overall

1. Jie Yang
2. Jinyu Li
3. Jacob Buckman
4. Baosong Yang
5. Julian Salazar
6. Linhao Dong
7. Jing-jing Chen
8. Graham Neubig
9. Emiru Tsunoo
10. Fengshun Xiao

Papers from Matthias Sperber's perspective

Ordered by how strongly the researchers Matthias Sperber 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. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
9. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Self-Attentional Acoustic Models (2018) — 160 citations
• Neural Lattice-to-Sequence Models for Uncertain Inputs (2017) — 81 citations
• Speech Translation and the End-to-End Promise: Taking Stock of Where We Are (2020) — 126 citations
• The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018 (2018) — 10 citations
• Open Source Toolkit for Speech to Text Translation (2018) — 14 citations
• Toward Robust Neural Machine Translation for Noisy Input Sequences (2017) — 81 citations