Stephan Mandt

Artificial Intelligence · with Jenatton · 2020

A researcher in the Science corpus: 3 papers; trusts 3 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 44 citations into it
• Optimization & Training — 11 citations into it

Whom Stephan Mandt trusts overall

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

1. Xavier Glorot
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Diederik P. Kingma

Papers from Stephan Mandt's perspective

Ordered by how strongly the researchers Stephan Mandt 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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
3. Going deeper with convolutions
4. ImageNet classification with deep convolutional neural networks
5. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
6. Distilling the Knowledge in a Neural Network (arXiv.org)
7. Gradient-based learning applied to document recognition
8. Understanding the difficulty of training deep feedforward neural networks
9. Learning Multiple Layers of Features from Tiny Images
10. Attention is All you Need (Neural Information Processing Systems)

Their papers

• Hydra: Preserving Ensemble Diversity for Model Distillation (2020) — 65 citations
• Appendix for: How Good is the Bayes Posterior in Deep Neural Networks Really? (2020) — 424 citations
• The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks (2020) — 55 citations