Thomas Elsken

Artificial Intelligence · 2017–2020

A researcher in the Science corpus: 5 papers; trusts 508 researchers and is trusted by 66 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 160 citations into it; #3,927 of 35,345 by trust here, #6,064 by citations
• Computer Vision and Pattern Recognition — 121 citations into it; #4,870 of 21,575 by trust here, #6,542 by citations
• Neural Architecture Search & AutoML — 68 citations into it; #23 of 283 by trust here, #23 by citations
• Model Architectures — 59 citations into it
• Optimization & Training — 55 citations into it
• Efficiency & Compression — 23 citations into it
• Evaluation & Benchmarks — 14 citations into it
• Reinforcement Learning — 9 citations into it

Whom Thomas Elsken trusts overall

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

1. Geoffrey E. Hinton
2. Barret Zoph
3. Alex Krizhevsky
4. Yoshua Bengio
5. Kaiming He
6. Ilya Loshchilov
7. Quoc V. Le
8. Frank Hutter
9. Karen Simonyan
10. Ilya Sutskever

Who trusts Thomas Elsken overall

1. Arber Zela
2. Haifeng Jin
3. Colin White
4. Frank Hutter
5. Tonmoy Saikia
6. Lemeng Wu
7. Qingquan Song
8. Jie Hu
9. Han Cai
10. Zhichao Lu

Papers from Thomas Elsken's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
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. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Going deeper with convolutions

Their papers

• Simple And Efficient Architecture Search for Convolutional Neural Networks (2017) — 245 citations
• Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution (2018) — 546 citations
• Understanding and Robustifying Differentiable Architecture Search (2019) — 415 citations
• Neural Ensemble Search for Performant and Calibrated Predictions (2020) — 41 citations
• Multi-objective Architecture Search for CNNs (2018) — 59 citations