W. James Murdoch

Artificial Intelligence · 2016–2019

A researcher in the Science corpus: 5 papers; trusts 361 researchers and is trusted by 38 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 140 citations into it; #4,618 of 35,345 by trust here, #5,533 by citations
• Safety, Robustness & Interpretability — 93 citations into it; #334 of 2,251 by trust here, #807 by citations
• Computer Vision and Pattern Recognition — 70 citations into it; #11,352 of 21,575 by trust here, #15,529 by citations
• Natural Language Processing — 44 citations into it; #1,603 of 5,688 by trust here, #2,497 by citations
• Model Architectures — 22 citations into it
• Evaluation & Benchmarks — 13 citations into it
• Biophysics — 11 citations into it
• Safety Research — 8 citations into it

Whom W. James Murdoch trusts overall

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

1. Geoffrey E. Hinton
2. Richard Socher
3. Diederik P. Kingma
4. Ilya Sutskever
5. Yann LeCun
6. Yoshua Bengio
7. Alex Krizhevsky
8. Sepp Hochreiter
9. Matthew D. Zeiler
10. Kaiming He

Who trusts W. James Murdoch overall

1. Chandan Singh
2. Xisen Jin
3. Gabrielle Ras
4. Tian Guo
5. Yao Ming
6. Bin Yu
7. Michael Sejr Schlichtkrull
8. Nicola De Cao
9. Laura Rieger
10. Yonatan Belinkov

Papers from W. James Murdoch's perspective

Ordered by how strongly the researchers W. James Murdoch 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. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
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. ImageNet Large Scale Visual Recognition Challenge
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs (2018) — 223 citations
• Automatic Rule Extraction from Long Short Term Memory Networks (2016) — 95 citations
• Hierarchical interpretations for neural network predictions (2018) — 162 citations
• Definitions, methods, and applications in interpretable machine learning (2019) — 1,811 citations
• Interpretations are useful: penalizing explanations to align neural networks with prior knowledge (2019) — 258 citations