David Pfau

Artificial Intelligence · 2016–2019

A researcher in the Science corpus: 9 papers; trusts 309 researchers and is trusted by 935 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 122 citations into it; #1,531 of 35,345 by trust here, #1,551 by citations
• Computer Vision and Pattern Recognition — 111 citations into it; #1,441 of 21,575 by trust here, #1,134 by citations
• Generative Models — 57 citations into it; #217 of 1,956 by trust here, #302 by citations
• Representation & Self-Supervised Learning — 48 citations into it
• Optimization & Training — 40 citations into it; #1,291 of 2,601 by trust here, #278 by citations
• Reinforcement Learning — 39 citations into it; #838 of 2,242 by trust here, #1,280 by citations
• Model Architectures — 24 citations into it
• Computational Theory and Mathematics — 20 citations into it

Whom David Pfau trusts overall

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

1. Yoshua Bengio
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Diederik P. Kingma
5. Dimitri P. Bertsekas
6. Yann LeCun
7. Richard S. Sutton
8. J. Urgen Schmidhuber
9. Ilya Sutskever
10. Andrew Y. Ng

Who trusts David Pfau overall

1. Garrett Wilson
2. Gauthier Gidel
3. Florian Schäfer
4. Yuxi Li
5. Diane Joyce Cook
6. Ian J. Goodfellow
7. Yongjun Hong
8. Chelsea Finn
9. Sergey Levine
10. Zhe Gan

Papers from David Pfau's perspective

Ordered by how strongly the researchers David Pfau 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. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Learning to learn by gradient descent by gradient descent (2016) — 2,222 citations
• Unrolled Generative Adversarial Networks (2016) — 1,076 citations
• Towards a Definition of Disentangled Representations (2018) — 546 citations
• Convolution by Evolution: Differentiable Pattern Producing Networks (2016) — 106 citations
• Connecting Generative Adversarial Networks and Actor-Critic Methods (2016) — 197 citations
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks (2019) — 609 citations
• Spectral Inference Networks: Unifying Spectral Methods With Deep Learning (2018) — 10 citations
• Spectral Inference Networks: Unifying Deep and Spectral Learning (2018) — 50 citations
• Simultaneous Denoising, Deconvolution, and Demixing of Calcium Imaging Data (2016) — 1,017 citations