Matthew J. Johnson

Artificial Intelligence · with Adams · 2012–2020

A researcher in the Science corpus: 11 papers; trusts 120 researchers and is trusted by 16 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 137 citations into it; #12,782 of 35,345 by trust here, #7,310 by citations
• Reinforcement Learning — 57 citations into it; #1,465 of 2,242 by trust here, #1,204 by citations
• Probabilistic & Bayesian Methods — 39 citations into it; #948 of 1,525 by trust here, #355 by citations
• Computer Vision and Pattern Recognition — 36 citations into it
• Statistics and Probability — 34 citations into it
• Control and Systems Engineering — 32 citations into it
• Optimization & Training — 24 citations into it
• Representation & Self-Supervised Learning — 21 citations into it; #1,548 of 3,145 by trust here, #856 by citations

Whom Matthew J. Johnson trusts overall

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

1. Michael I. Jordan
2. Diederik P. Kingma
3. Zoubin Ghahramani
4. Geoffrey E. Hinton
5. Yoshua Bengio
6. David M. Blei
7. Radford M. Neal
8. Matthew D. Hoffman
9. Alex Krizhevsky
10. Yann LeCun

Who trusts Matthew J. Johnson overall

1. Chia-ying Lee
2. Peter Sorrenson
3. Jason Tyler Rolfe
4. Sergey Levine
5. Chelsea Finn
6. Ricard Marxer
7. Diederik P. Kingma
8. Sandeep R. Datta
9. Dustin Tran
10. Cheng Zhang

Papers from Matthew J. Johnson's perspective

Ordered by how strongly the researchers Matthew J. Johnson 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. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Composing graphical models with neural networks for structured representations and fast inference (2016) — 520 citations
• SOLAR: Deep Structured Latent Representations for Model-Based Reinforcement Learning (2018) — 42 citations
• Dependent Multinomial Models Made Easy: Stick-Breaking with the Polya-gamma Augmentation (2015) — 107 citations
• Learning Differential Equations that are Easy to Solve (2020) — 131 citations
• Estimating the Spectral Density of Large Implicit Matrices (2018) — 40 citations
• SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning (2018) — 236 citations
• Bayesian Learning and Inference in Recurrent Switching Linear Dynamical Systems (2017) — 309 citations
• Structured VAEs: Composing Probabilistic Graphical Models and Variational Autoencoders (2016) — 27 citations
• Mapping Sub-Second Structure in Mouse Behavior. (2015) — 735 citations
• Stochastic Variational Inference for Bayesian Time Series Models (2014) — 87 citations
• Bayesian nonparametric hidden semi-Markov models (2012) — 377 citations