Michael Collins

Artificial Intelligence · with Cohen · 2011–2018

A researcher in the Science corpus: 7 papers; trusts 108 researchers and is trusted by 46 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 52 citations into it; #5,412 of 35,345 by trust here, #15,542 by citations
• Natural Language Processing — 32 citations into it; #2,770 of 5,688 by trust here, #4,682 by citations
• Computer Vision and Pattern Recognition — 24 citations into it
• Optimization & Training — 16 citations into it
• Statistical Learning Theory — 12 citations into it
• Probabilistic & Bayesian Methods — 11 citations into it; #467 of 1,525 by trust here, #921 by citations
• Model Architectures — 10 citations into it
• Representation & Self-Supervised Learning — 10 citations into it

Whom Michael Collins trusts overall

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

1. Philipp Koehn
2. Franz Joseph Och
3. Yoshua Bengio
4. Michael Collins
5. Geoffrey E. Hinton
6. Ilya Sutskever
7. Mitchell P. Marcus
8. Daniel Klein
9. Alex Krizhevsky
10. Tomas Mikolov

Who trusts Michael Collins overall

1. Anton Bakhtin
2. Yuntian Deng
3. Alexander M. Rush
4. Nanyun Peng
5. Philip Bachman
6. Ruben Cartuyvels
7. Jieyu Zhao
8. Kevin Clark
9. Kai-Wei Chang
10. Benjamin Eysenbach

Papers from Michael Collins's perspective

Ordered by how strongly the researchers Michael Collins 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. 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. Learning Multiple Layers of Features from Tiny Images
9. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency (2018) — 180 citations
• A Tutorial on Dual Decomposition and Lagrangian Relaxation for Inference in Natural Language Processing (2012) — 124 citations
• A Provably Correct Learning Algorithm for Latent-Variable PCFGs (2014) — 15 citations
• How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets (2014) — 66 citations
• Approximate PCFG Parsing Using Tensor Decomposition (2013) — 25 citations
• Advances in Neural Information Processing Systems 25 (2012) — 208 citations
• Exact Decoding of Phrase-Based Translation Models through Lagrangian Relaxation (2011) — 60 citations