Kazuki Osawa

Artificial Intelligence · 2018–2019

A researcher in the Science corpus: 3 papers; trusts 52 researchers and is trusted by 4 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 69 citations into it; #30,152 of 35,345 by trust here, #17,412 by citations
• Optimization & Training — 53 citations into it; #1,898 of 2,601 by trust here, #1,766 by citations
• Computer Vision and Pattern Recognition — 39 citations into it; #18,492 of 21,575 by trust here, #11,721 by citations
• Probabilistic & Bayesian Methods — 21 citations into it
• Statistical and Nonlinear Physics — 9 citations into it
• Model Architectures — 7 citations into it; #1,909 of 2,278 by trust here, #2,037 by citations

Whom Kazuki Osawa trusts overall

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

1. James Martens
2. Geoffrey E. Hinton
3. Roger Baker Grosse
4. Alex Krizhevsky
5. Kaiming He
6. Radford M. Neal
7. Yoshua Bengio
8. Jimmy Ba
9. Alex Graves
10. Diederik P. Kingma

Who trusts Kazuki Osawa overall

1. Tal Ben-Nun
2. Elad Hoffer
3. Sidak Pal Singh
4. Leonard Adolphs
5. Dan Alistarh
6. Jonas Köhler
7. Torsten Hoefler
8. Elias Frantar
9. Mohammad Emtiyaz Khan
10. Sebastian Farquhar

Papers from Kazuki Osawa's perspective

Ordered by how strongly the researchers Kazuki Osawa 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. Gradient-based learning applied to document recognition
6. Long Short-Term Memory
7. Attention is All you Need (Neural Information Processing Systems)
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. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Practical Deep Learning with Bayesian Principles (2019) — 280 citations
• Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks (2018) — 102 citations
• Second-order Optimization Method for Large Mini-batch: Training ResNet-50 on ImageNet in 35 Epochs (2018) — 39 citations