Pascal Germain

Artificial Intelligence · 2009–2016

A researcher in the Science corpus: 9 papers; trusts 89 researchers and is trusted by 303 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 123 citations into it; #3,112 of 35,345 by trust here, #1,189 by citations
• Statistical Learning Theory — 76 citations into it; #466 of 1,038 by trust here, #417 by citations
• Computer Vision and Pattern Recognition — 47 citations into it; #2,407 of 21,575 by trust here, #1,070 by citations
• Representation & Self-Supervised Learning — 43 citations into it; #767 of 3,145 by trust here, #163 by citations
• Probabilistic & Bayesian Methods — 35 citations into it; #701 of 1,525 by trust here, #668 by citations
• Management Science and Operations Research — 28 citations into it
• Statistics and Probability — 24 citations into it
• Computational Mechanics — 14 citations into it

Whom Pascal Germain trusts overall

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

1. David A. McAllester
2. J. Langford
3. Olivier Catoni
4. John Shawe-Taylor
5. Arindam Banerjee
6. Andreas Maurer
7. Yevgeny Seldin
8. François Laviolette
9. Shai Ben-David
10. Leo Breiman

Who trusts Pascal Germain overall

1. Pierre Alquier
2. Wouter M. Kouw
3. Ben London
4. Yevgeny Seldin
5. Anastasia Pentina
6. François Laviolette
7. Mingsheng Long
8. Luc Bégin
9. Corinna Cortes
10. Yuchen Zhang

Papers from Pascal Germain's perspective

Ordered by how strongly the researchers Pascal Germain 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. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. Learning Multiple Layers of Features from Tiny Images
8. ImageNet: A large-scale hierarchical image database
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

• Domain-Adversarial Training of Neural Networks (2015) — 11,758 citations
• Domain-Adversarial Neural Networks (2014) — 351 citations
• PAC-Bayesian learning of linear classifiers (2009) — 268 citations
• PAC-Bayesian Theory Meets Bayesian Inference (2016) — 214 citations
• A New PAC-Bayesian Perspective on Domain Adaptation (2015) — 71 citations
• PAC-Bayesian Bounds based on the Rényi Divergence (2016) — 96 citations
• Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm (2015) — 156 citations
• PAC-Bayesian Theory for Transductive Learning (2014) — 52 citations
• Supplementary Material to A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers (2013)