Johannes von Oswald

Artificial Intelligence · 2018–2022

A researcher in the Science corpus: 8 papers; trusts 465 researchers and is trusted by 30 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 328 citations into it
• Computer Vision and Pattern Recognition — 190 citations into it
• Optimization & Training — 91 citations into it
• Meta & Continual Learning — 88 citations into it; #171 of 1,041 by trust here, #226 by citations
• Model Architectures — 68 citations into it
• Probabilistic & Bayesian Methods — 63 citations into it
• Representation & Self-Supervised Learning — 63 citations into it
• Generative Models — 52 citations into it

Whom Johannes von Oswald trusts overall

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

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Yoshua Bengio
5. Kaiming He
6. J. Urgen Schmidhuber
7. Yann LeCun
8. Sepp Hochreiter
9. Jimmy Ba
10. Ilya Sutskever

Who trusts Johannes von Oswald overall

1. Gyuhak Kim
2. Christian Henning
3. Zixuan Ke
4. Yiduo Guo
5. James Smith
6. Changnan Xiao
7. Benjamin Ehret
8. Bing Liu
9. Jorge Armando Mendez Mendez
10. Vinay Kumar Verma

Papers from Johannes von Oswald's perspective

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

• Learning where to learn: Gradient sparsity in meta and continual learning (2021) — 60 citations
• Posterior Meta-Replay for Continual Learning (2021) — 76 citations
• Transformers learn in-context by gradient descent (2022) — 821 citations
• Continual learning in recurrent neural networks (2020) — 52 citations
• Neural networks with late-phase weights (2020) — 40 citations
• Continual Learning in Recurrent Neural Networks with Hypernetworks (2020) — 10 citations
• Continual learning with hypernetworks (2019) — 428 citations
• Approximating the Predictive Distribution via Adversarially-Trained Hypernetworks (2018)