Shun-ichi Amari
Artificial Intelligence · 1967–2018
A researcher in the Science corpus: 44 papers; trusts 174 researchers and is trusted by 9,199 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 133 citations into it; #126 of 36,961 by trust here, #1,273 by citations
- Signal Processing — 62 citations into it; #227 of 7,592 by trust here, #364 by citations
- Computer Vision and Pattern Recognition — 55 citations into it; #3,739 of 21,973 by trust here, #6,608 by citations
- Statistics and Probability — 46 citations into it; #498 of 13,188 by trust here, #956 by citations
- Optimization & Training — 45 citations into it; #41 of 2,605 by trust here, #173 by citations
- Computational Mechanics — 31 citations into it; #1,175 of 10,021 by trust here, #2,214 by citations
- Model Architectures — 29 citations into it; #1,468 of 2,288 by trust here, #1,982 by citations
- Statistical and Nonlinear Physics — 27 citations into it; #745 of 10,175 by trust here, #1,318 by citations
Whom Shun-ichi Amari trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Anthony J. Bell
- Howard H. Yang
- Calyampudi R. Rao
- Andrzej S. Cichocki
- David E. Rumelhart
- Hirotugu Akaike
- Terrence J. Sejnowski
- Geoffrey E. Hinton
- Te Sun Han
- Jorma Rissanen
Who trusts Shun-ichi Amari overall
- Yoshua Bengio
- James Martens
- L. Eon Bottou
- Sergey Levine
- Geoffrey E. Hinton
- Ruslan Salakhutdinov
- J. Urgen Schmidhuber
- Quoc V. Le
- Andrzej S. Cichocki
- Razvan Pascanu
Papers from Shun-ichi Amari's perspective
Ordered by how strongly the researchers Shun-ichi Amari trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Gradient-based learning applied to document recognition
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Learning Multiple Layers of Features from Tiny Images
- GENERATIVE ADVERSARIAL NETS
Their papers
- Natural Gradient Works Efficiently in Learning (1998)
- Methods of information geometry (2000) — 2,797 citations
- A New Learning Algorithm for Blind Signal Separation (1995)
- Neural Learning in Structured Parameter Spaces - Natural Riemannian Gradient (1996)
- Natural gradient descent for on-line learning (1998)
- Adaptive Method of Realizing Natural Gradient Learning for Multilayer Perceptrons (2000) — 219 citations
- Adaptive natural gradient learning algorithms for various stochastic models (2000) — 180 citations
- Universal statistics of Fisher information in deep neural networks: mean field approach (2018) — 187 citations
- Local minima and plateaus in hierarchical structures of multilayer perceptrons (2000) — 245 citations
- Four Types of Learning Curves (1992)
- Statistical Theory of Learning Curves under Entropic Loss Criterion (1993)
- Complexity Issues in Natural Gradient Descent Method for Training Multilayer Perceptrons (1998)
- Information geometry of Boltzmann machines (1992)
- Information geometry on hierarchy of probability distributions (2001) — 454 citations
- A universal theorem on learning curves (1993)
- Adaptive blind signal and image processing (2002) — 1,499 citations
- Conformal Transformation of Kernel Functions: A Data-Dependent Way to Improve Support Vector Machine Classifiers (2002) — 110 citations
- Geometrical Singularities in the Neuromanifold of Multilayer Perceptrons (2001) — 36 citations
- Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements (1972)
- Interpolating between Optimal Transport and MMD using Sinkhorn Divergences (2018) — 706 citations