Ryo Karakida

Artificial Intelligence · 2018–2021

A researcher in the Science corpus: 2 papers; trusts 55 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 52 citations into it; #12,636 of 35,345 by trust here, #17,776 by citations
• Optimization & Training — 23 citations into it
• Scaling & Learning Theory — 22 citations into it; #177 of 428 by trust here, #303 by citations
• Computer Vision and Pattern Recognition — 20 citations into it
• Statistical and Nonlinear Physics — 13 citations into it; #2,804 of 10,127 by trust here, #3,979 by citations
• Model Architectures — 11 citations into it
• Statistical Learning Theory — 10 citations into it; #572 of 1,038 by trust here, #602 by citations
• Computational Mechanics — 8 citations into it

Whom Ryo Karakida trusts overall

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

1. Jeffrey Pennington
2. Shun-ichi Amari
3. Greg Yang
4. Sam Schoenholz
5. Yoshua Bengio
6. Geoffrey E. Hinton
7. Yann LeCun
8. L. Eon Bottou
9. Alex Krizhevsky
10. James Martens

Who trusts Ryo Karakida overall

1. Greg Yang
2. Lechao Xiao
3. Daniel S. Park
4. Piotr A. Sokól
5. Zhiwei Jia
6. Jascha Narain Sohl-Dickstein
7. Jimmy Ba
8. Roman Novak
9. Amira Abbas
10. Hao Su

Papers from Ryo Karakida's perspective

Ordered by how strongly the researchers Ryo Karakida 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. Gradient-based learning applied to document recognition
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Attention is All you Need (Neural Information Processing Systems)
6. Long Short-Term Memory
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. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Universal statistics of Fisher information in deep neural networks: mean field approach (2018) — 187 citations
• Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting (2021) — 16 citations