Mathijs Mul

Artificial Intelligence · 2017–2020

A researcher in the Science corpus: 4 papers; trusts 72 researchers and is trusted by 4 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 75 citations into it; #24,005 of 35,345 by trust here, #19,439 by citations
• Natural Language Processing — 66 citations into it
• Model Architectures — 35 citations into it
• Safety Research — 33 citations into it
• Sociology and Political Science — 26 citations into it
• Computer Vision and Pattern Recognition — 19 citations into it
• Representation & Self-Supervised Learning — 18 citations into it; #2,377 of 3,145 by trust here, #2,355 by citations
• Computational Linguistics & Semantics — 16 citations into it

Whom Mathijs Mul trusts overall

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

1. Jeffrey L. Elman
2. Samuel R. Bowman
3. Sepp Hochreiter
4. Christopher D. Manning
5. Geoffrey E. Hinton
6. Gary F. Marcus
7. Ilya Sutskever
8. Yoshua Bengio
9. Richard Socher
10. J. Urgen Schmidhuber

Who trusts Mathijs Mul overall

1. Ofir Press
2. Dieuwke Hupkes

Papers from Mathijs Mul's perspective

Ordered by how strongly the researchers Mathijs Mul 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. Attention is All you Need (Neural Information Processing Systems)
4. Long Short-Term Memory
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. Gradient-based learning applied to document recognition
7. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
8. ImageNet: A large-scale hierarchical image database
9. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
10. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)

Their papers

• Compositionality Decomposed: How do Neural Networks Generalise? (2019) — 408 citations
• Compositionality Decomposed: How do Neural Networks Generalise? (Extended Abstract) (2020) — 29 citations
• Siamese recurrent networks learn first-order logic reasoning and exhibit zero-shot compositional generalization (2019) — 18 citations
• What's the right thing to do? Increasing pro-sociality with simple moral nudges (2017) — 113 citations