Kurt Wan-Duo Ma

Artificial Intelligence · 2017

A researcher in the Science corpus: 1 paper; trusts 5 researchers and is trusted by 2 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 19 citations into it; #30,380 of 35,345 by trust here, #12,083 by citations
• Optimization & Training — 14 citations into it
• Model Architectures — 13 citations into it; #1,928 of 2,278 by trust here, #1,168 by citations
• Computer Vision and Pattern Recognition — 11 citations into it; #18,665 of 21,575 by trust here, #8,409 by citations

Whom Kurt Wan-Duo Ma trusts overall

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

1. Kaiming He
2. Yoshua Bengio
3. Diederik P. Kingma

Who trusts Kurt Wan-Duo Ma overall

1. Yann Dauphin
2. Sam Schoenholz

Papers from Kurt Wan-Duo Ma's perspective

Ordered by how strongly the researchers Kurt Wan-Duo Ma 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. Going deeper with convolutions
5. Gradient-based learning applied to document recognition
6. Understanding the difficulty of training deep feedforward neural networks
7. A Fast Learning Algorithm for Deep Belief Nets
8. Long Short-Term Memory
9. Learning Multiple Layers of Features from Tiny Images
10. Attention is All you Need (Neural Information Processing Systems)

Their papers

• The Shattered Gradients Problem: If resnets are the answer, then what is the question? (2017) — 465 citations