Ming Li

Artificial Intelligence · with Zhou · 2005–2010

A researcher in the Science corpus: 4 papers; trusts 52 researchers and is trusted by 58 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 38 citations into it; #3,596 of 35,345 by trust here, #9,170 by citations
• Natural Language Processing — 16 citations into it
• Computer Vision and Pattern Recognition — 12 citations into it
• Representation & Self-Supervised Learning — 9 citations into it
• Evaluation & Benchmarks — 7 citations into it; #473 of 3,147 by trust here, #1,517 by citations
• Model Architectures — 5 citations into it
• Optimization & Training — 5 citations into it
• Statistics and Probability — 5 citations into it

Whom Ming Li trusts overall

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

1. Leo Breiman
2. Zhi-Hua Zhou
3. Thorsten Joachims
4. Jerome H. Friedman
5. Kamal Nigam
6. Avrim Blum
7. Arthur P. Dempster
8. Tin Kam Ho
9. Sally A. Goldman
10. Yoav Freund

Who trusts Ming Li overall

1. Mohamed Farouk Abdel Hady
2. Zhi-Hua Zhou
3. Jesper E. van Engelen
4. Isaac Triguero
5. Friedhelm Schwenker
6. Chang Xu
7. Anders Søgaard
8. Holger H. Hoos
9. Yuji Roh
10. Dacheng Tao

Papers from Ming Li's perspective

Ordered by how strongly the researchers Ming Li 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. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Tri-training: exploiting unlabeled data using three classifiers (2005) — 1,189 citations
• Semi-supervised learning by disagreement (2010) — 360 citations
• Improve Computer-Aided Diagnosis With Machine Learning Techniques Using Undiagnosed Samples (2007) — 382 citations
• Semi-Supervised Regression with Co-Training (2005) — 316 citations