Masashi Sugiyama
Artificial Intelligence · 2005–2022
A researcher in the Science corpus: 63 papers; trusts 2,124 researchers and is trusted by 1,362 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 920 citations into it; #857 of 36,961 by trust here, #826 by citations
- Computer Vision and Pattern Recognition — 340 citations into it; #3,742 of 21,973 by trust here, #2,773 by citations
- Statistics and Probability — 326 citations into it; #515 of 13,188 by trust here, #433 by citations
- Optimization & Training — 197 citations into it; #1,177 of 2,605 by trust here, #606 by citations
- Statistical Learning Theory — 175 citations into it; #339 of 1,040 by trust here, #195 by citations
- Representation & Self-Supervised Learning — 160 citations into it; #1,073 of 3,156 by trust here, #550 by citations
- Safety, Robustness & Interpretability — 111 citations into it; #771 of 2,259 by trust here, #1,188 by citations
- Computational Theory and Mathematics — 108 citations into it; #4,555 of 12,489 by trust here, #2,127 by citations
Whom Masashi Sugiyama trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Bernhard Schölkopf
- Alex Krizhevsky
- Lotfi A. Zadeh
- Radford M. Neal
- Alex Smola
- Yoshua Bengio
- Michael I. Jordan
- Yann LeCun
- Diederik P. Kingma
Who trusts Masashi Sugiyama overall
- Balaji Lakshminarayanan
- Qiang Yang
- Hirotaka Hachiya
- Wouter M. Kouw
- Song Liu
- Dacheng Tao
- Amos J. Storkey
- Junfeng Wen
- Mingsheng Long
- Bernhard Schölkopf
Papers from Masashi Sugiyama's perspective
Ordered by how strongly the researchers Masashi Sugiyama trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Dataset Shift in Machine Learning (2009) — 2,271 citations
- Bayesian dark knowledge (2015) — 271 citations
- Covariate Shift by Kernel Mean Matching (2009) — 699 citations
- Covariate Shift Adaptation by Importance Weighted Cross Validation (2007) — 1,089 citations
- Density Ratio Estimation in Machine Learning (2012) — 696 citations
- Direct Importance Estimation with Model Selection and Its Application to Covariate Shift Adaptation (2007) — 962 citations
- Learning Discrete Representations via Information Maximizing Self-Augmented Training (2017) — 495 citations
- Co-teaching: Robust training of deep neural networks with extremely noisy labels (2018) — 2,654 citations
- Does Distributionally Robust Supervised Learning Give Robust Classifiers? (2016) — 253 citations
- Direct importance estimation for covariate shift adaptation (2008) — 498 citations
- Parametric Return Density Estimation for Reinforcement Learning (2010) — 120 citations
- When Training and Test Sets Are Different: Characterizing Learning Transfer (2009) — 310 citations
- Nonparametric Return Distribution Approximation for Reinforcement Learning (2010) — 125 citations
- Mixture Regression for Covariate Shift (2006) — 125 citations
- Machine Learning in Non-Stationary Environments - Introduction to Covariate Shift Adaptation (2012) — 132 citations
- Clustering via Mode Seeking by Direct Estimation of the Gradient of a Log-Density (2014) — 46 citations
- Input-dependent estimation of generalization error under covariate shift (2005) — 158 citations
- Positive-Unlabeled Learning with Non-Negative Risk Estimator (2017) — 603 citations
- Attacks Which Do Not Kill Training Make Adversarial Learning Stronger (2020) — 456 citations
- Faster Stochastic Variational Inference using Proximal-Gradient Methods with General Divergence Functions (2015) — 58 citations