Jörn-Henrik Jacobsen
Artificial Intelligence · 2016–2020
A researcher in the Science corpus: 18 papers; trusts 1,776 researchers and is trusted by 741 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 538 citations into it; #1,878 of 36,961 by trust here, #2,426 by citations
- Computer Vision and Pattern Recognition — 408 citations into it; #2,223 of 21,973 by trust here, #2,631 by citations
- Safety, Robustness & Interpretability — 195 citations into it; #1,232 of 2,259 by trust here, #537 by citations
- Generative Models — 119 citations into it; #457 of 1,963 by trust here, #582 by citations
- Representation & Self-Supervised Learning — 82 citations into it
- Probabilistic & Bayesian Methods — 76 citations into it; #1,136 of 1,526 by trust here, #485 by citations
- Model Architectures — 67 citations into it; #532 of 2,288 by trust here, #991 by citations
- Signal Processing — 67 citations into it; #6,584 of 7,592 by trust here, #2,455 by citations
Whom Jörn-Henrik Jacobsen trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Yoshua Bengio
- Yann LeCun
- Ilya Sutskever
- Christian Szegedy
- Stéphane Mallat
- Ross B. Girshick
Who trusts Jörn-Henrik Jacobsen overall
- Jens Behrmann
- Yang Song
- Lynton Ardizzone
- David Kristjanson Duvenaud
- Ricky T. Q. Chen
- Polina Kirichenko
- Eric T. Nalisnick
- Ethan Fetaya
- George Papamakarios
- Eugene Belilovsky
Papers from Jörn-Henrik Jacobsen's perspective
Ordered by how strongly the researchers Jörn-Henrik Jacobsen 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Shortcut learning in deep neural networks (2020) — 3,155 citations
- Invertible Residual Networks (2018) — 728 citations
- Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One (2019) — 664 citations
- i-RevNet: Deep Invertible Networks (2018) — 360 citations
- Excessive Invariance Causes Adversarial Vulnerability (2018) — 174 citations
- Residual Flows for Invertible Generative Modeling (2019) — 450 citations
- Out-of-Distribution Generalization via Risk Extrapolation (REx) (2020) — 1,228 citations
- Flexibly Fair Representation Learning by Disentanglement (2019) — 383 citations
- Multiscale Hierarchical Convolutional Networks (2017) — 17 citations
- How to train your neural ODE (2020) — 366 citations
- Structured Receptive Fields in CNNs (2016) — 117 citations
- Environment Inference for Invariant Learning (2020) — 469 citations
- Conditional Generative Models are not Robust (2019) — 16 citations
- Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness (2019) — 48 citations
- Understanding the Limitations of Conditional Generative Models (2019) — 65 citations
- Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations (2020) — 104 citations
- Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling (2020) — 100 citations
- Dynamic Steerable Blocks in Deep Residual Networks (2017) — 28 citations