Akihiro Matsukawa

Artificial Intelligence · 2013–2019

A researcher in the Science corpus: 6 papers; trusts 186 researchers and is trusted by 18 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 97 citations into it; #19,407 of 35,345 by trust here, #8,893 by citations
• Computer Vision and Pattern Recognition — 77 citations into it; #6,185 of 21,575 by trust here, #3,404 by citations
• Generative Models — 37 citations into it; #704 of 1,956 by trust here, #569 by citations
• Probabilistic & Bayesian Methods — 30 citations into it; #1,213 of 1,525 by trust here, #945 by citations
• Statistics and Probability — 29 citations into it
• Signal Processing — 22 citations into it
• Evaluation & Benchmarks — 15 citations into it
• Computer Networks and Communications — 13 citations into it

Whom Akihiro Matsukawa trusts overall

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

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Yoshua Bengio
5. Danilo Jimenez Rezende
6. Tommi S. Jaakkola
7. Yann LeCun
8. Kaiming He
9. Michael I. Jordan
10. Radford M. Neal

Who trusts Akihiro Matsukawa overall

1. Erik A. Daxberger
2. Joost R. van Amersfoort
3. Eric T. Nalisnick
4. Yilun Du
5. Jie Jessie Ren
6. Pavel Izmailov
7. José Miguel Hernández-Lobato
8. Yee Whye Teh
9. Jeffrey Mahler
10. Polina Kirichenko

Papers from Akihiro Matsukawa's perspective

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

Their papers

• Do Deep Generative Models Know What They Don't Know? (2018) — 882 citations
• Hybrid Models with Deep and Invertible Features (2019) — 105 citations
• Cloud-based robot grasping with the google object recognition engine (2013) — 270 citations
• Detecting Out-of-Distribution Inputs to Deep Generative Models Using a Test for Typicality (2019) — 85 citations
• Improved Knowledge Distillation via Teacher Assistant (2019) — 1,428 citations
• Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality (2019) — 170 citations