Takuya Akiba

Artificial Intelligence · 2013–2019

A researcher in the Science corpus: 8 papers; trusts 366 researchers and is trusted by 23 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 92 citations into it; #9,531 of 35,345 by trust here, #5,682 by citations
• Computer Vision and Pattern Recognition — 83 citations into it; #7,127 of 21,575 by trust here, #6,795 by citations
• Optimization & Training — 40 citations into it; #1,052 of 2,601 by trust here, #1,034 by citations
• Model Architectures — 26 citations into it
• Safety, Robustness & Interpretability — 26 citations into it
• Statistical and Nonlinear Physics — 19 citations into it
• Signal Processing — 12 citations into it
• Computational Theory and Mathematics — 11 citations into it; #9,946 of 12,182 by trust here, #2,565 by citations

Whom Takuya Akiba trusts overall

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

1. Alex Krizhevsky
2. Kaiming He
3. Geoffrey E. Hinton
4. Ross B. Girshick
5. Ilya Sutskever
6. Yoshua Bengio
7. Diederik P. Kingma
8. Christian Szegedy
9. Yann LeCun
10. Shaoqing Ren

Who trusts Takuya Akiba overall

1. Kazuki Osawa
2. Yang You
3. Nitish Shirish Keskar
4. Artur Meller
5. Albert S. Berahas
6. Cédric Renggli
7. Ivan Rubachev
8. Kenta Oono
9. Mahmoud Assran
10. Khan Muhammad

Papers from Takuya Akiba's perspective

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

Their papers

• Shakedrop Regularization for Deep Residual Learning (2018) — 179 citations
• Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes (2017) — 320 citations
• Optuna: A Next-generation Hyperparameter Optimization Framework (2019) — 10,668 citations
• Variance-based Gradient Compression for Efficient Distributed Deep Learning (2018) — 91 citations
• Adversarial Attacks and Defences Competition (2018) — 353 citations
• Computing Personalized PageRank Quickly by Exploiting Graph Structures (2014) — 84 citations
• Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects (2018) — 46 citations
• Fast exact shortest-path distance queries on large networks by pruned landmark labeling (2013) — 426 citations