Michael S. Pritchard

Atmospheric Science · 2018–2019

A researcher in the Science corpus: 3 papers; trusts 9 researchers and is trusted by 5 researchers here, as inferred from the citation graph.

Subfields

• Atmospheric Science — 57 citations into it; #2,043 of 4,804 by trust here, #1,314 by citations
• Global and Planetary Change — 56 citations into it; #4,135 of 10,225 by trust here, #3,280 by citations
• Artificial Intelligence — 20 citations into it
• Oceanography — 6 citations into it
• Optimization & Training — 6 citations into it

Whom Michael S. Pritchard trusts overall

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

1. Diederik P. Kingma
2. M. Khairoutdinov
3. David A. Randall
4. Jimmy Ba
5. Geoffrey E. Hinton
6. J. Andersen
7. Sandrine Bony
8. Alex Krizhevsky
9. Yann LeCun
10. Yoshua Bengio

Who trusts Michael S. Pritchard overall

1. Jared D. Willard
2. Peter Dueben
3. Chaopeng Shen
4. Stephan Rasp
5. Hugh Morrison
6. T. Bolton
7. Xiaowei Jia
8. Xianan Jiang

Papers from Michael S. Pritchard's perspective

Ordered by how strongly the researchers Michael S. Pritchard trusts endorse each paper. Same corpus, a different order for every researcher.

1. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
2. ImageNet classification with deep convolutional neural networks
3. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
4. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
5. ImageNet Large Scale Visual Recognition Challenge
6. Gradient-based learning applied to document recognition
7. Long Short-Term Memory
8. Attention is All you Need (Neural Information Processing Systems)
9. Dropout: a simple way to prevent neural networks from overfitting
10. ImageNet: A large-scale hierarchical image database

Their papers

• Enforcing Analytic Constraints in Neural Networks Emulating Physical Systems. (2019) — 364 citations
• Deep learning to represent subgrid processes in climate models (2018) — 892 citations
• Could Machine Learning Break the Convection Parameterization Deadlock? (2018) — 417 citations