Shinichi Shirakawa

Artificial Intelligence · 2017

A researcher in the Science corpus: 1 paper; trusts 69 researchers and is trusted by 34 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 34 citations into it; #6,306 of 35,345 by trust here, #11,921 by citations
• Computer Vision and Pattern Recognition — 24 citations into it
• Model Architectures — 17 citations into it; #540 of 2,278 by trust here, #1,145 by citations
• Optimization & Training — 13 citations into it
• Neural Architecture Search & AutoML — 7 citations into it; #44 of 283 by trust here, #107 by citations

Whom Shinichi Shirakawa trusts overall

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

1. Alex Krizhevsky
2. Yoshua Bengio
3. Kaiming He
4. Geoffrey E. Hinton
5. Diederik P. Kingma
6. James Bergstra
7. Julian Francis Miller
8. Yann LeCun
9. Sergey Ioffe
10. Christian Szegedy

Who trusts Shinichi Shirakawa overall

1. Yanan Sun
2. Thomas Elsken
3. Bing Xue
4. Martin Wistuba
5. Zhaobai Zhong
6. Mengjie Zhang
7. Ricardo H. R. Lima
8. Mohammad Mahdi Bejani
9. Bowen Baker
10. Jan Hendrik Metzen

Papers from Shinichi Shirakawa's perspective

Ordered by how strongly the researchers Shinichi Shirakawa 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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. Going deeper with convolutions

Their papers

• A genetic programming approach to designing convolutional neural network architectures (2017) — 618 citations