Lukas Schott

Artificial Intelligence · 2015–2020

A researcher in the Science corpus: 6 papers; trusts 265 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 150 citations into it; #13,516 of 35,345 by trust here, #9,369 by citations
• Computer Vision and Pattern Recognition — 110 citations into it
• Safety, Robustness & Interpretability — 100 citations into it; #924 of 2,251 by trust here, #1,047 by citations
• Representation & Self-Supervised Learning — 38 citations into it
• Signal Processing — 19 citations into it; #2,921 of 7,572 by trust here, #2,221 by citations
• Generative Models — 18 citations into it
• Evaluation & Benchmarks — 17 citations into it
• Optimization & Training — 17 citations into it

Whom Lukas Schott trusts overall

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

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Alex Krizhevsky
5. Christian Szegedy
6. Ian J. Goodfellow
7. Yann LeCun
8. Kaiming He
9. Ilya Sutskever
10. Jimmy Ba

Who trusts Lukas Schott overall

1. Jörn-Henrik Jacobsen
2. Florian Tramèr
3. Ethan Fetaya
4. Jens Behrmann
5. Nicholas Carlini
6. David Stutz
7. Bernhard Schölkopf
8. Will Grathwohl
9. Pratyush Maini
10. Richard S. Zemel

Papers from Lukas Schott's perspective

Ordered by how strongly the researchers Lukas Schott 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. Gradient-based learning applied to document recognition
5. ImageNet: A large-scale hierarchical image database
6. Attention is All you Need (Neural Information Processing Systems)
7. Long Short-Term Memory
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. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Towards the first adversarially robust neural network model on MNIST (2018) — 391 citations
• A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions (2020) — 243 citations
• Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding (2020) — 160 citations
• Increasing the robustness of DNNs against image corruptions by playing the Game of Noise (2020) — 66 citations
• Robust Perception through Analysis by Synthesis (2018) — 25 citations
• Comparative Study of Deep Learning Software Frameworks (2015) — 168 citations