Yann Dauphin
Artificial Intelligence · 2011–2021
A researcher in the Science corpus: 35 papers; trusts 2,640 researchers and is trusted by 12,917 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 830 citations into it; #145 of 36,961 by trust here, #190 by citations
- Computer Vision and Pattern Recognition — 465 citations into it; #283 of 21,973 by trust here, #318 by citations
- Natural Language Processing — 241 citations into it; #142 of 5,725 by trust here, #155 by citations
- Optimization & Training — 208 citations into it; #127 of 2,605 by trust here, #84 by citations
- Model Architectures — 168 citations into it; #219 of 2,288 by trust here, #135 by citations
- Efficiency & Compression — 97 citations into it; #396 of 1,273 by trust here, #324 by citations
- Representation & Self-Supervised Learning — 88 citations into it; #915 of 3,156 by trust here, #875 by citations
- Safety, Robustness & Interpretability — 55 citations into it; #1,269 of 2,259 by trust here, #558 by citations
Whom Yann Dauphin trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Kaiming He
- Diederik P. Kingma
- Alex Krizhevsky
- Ilya Sutskever
- Yann LeCun
- Ruslan Salakhutdinov
- James Martens
- Xavier Glorot
Who trusts Yann Dauphin overall
- Yoshua Bengio
- Chunyuan Li
- Kyunghyun Cho
- Quoc V. Le
- Angela Fan
- Mohit Bansal
- Zhe Gan
- Dacheng Tao
- Sergey Levine
- Trevor Darrell
Papers from Yann Dauphin's perspective
Ordered by how strongly the researchers Yann Dauphin trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Learning Multiple Layers of Features from Tiny Images
Their papers
- mixup: Beyond Empirical Risk Minimization (2017) — 12,076 citations
- Convolutional Sequence to Sequence Learning (2017) — 3,545 citations
- Language Modeling with Gated Convolutional Networks (2016) — 2,954 citations
- Hierarchical Neural Story Generation (2018) — 2,050 citations
- Identifying and attacking the saddle point problem in high-dimensional non-convex optimization (2014) — 1,536 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- Pay Less Attention with Lightweight and Dynamic Convolutions (2019) — 665 citations
- Parseval Networks: Improving Robustness to Adversarial Examples (2017) — 896 citations
- Better Mixing via Deep Representations (2012) — 356 citations
- The Manifold Tangent Classifier (2011) — 285 citations
- Deal or No Deal? End-to-End Learning of Negotiation Dialogues (2017) — 499 citations
- Fixup Initialization: Residual Learning Without Normalization (2019) — 406 citations
- A Convolutional Encoder Model for Neural Machine Translation (2016) — 466 citations
- Empirical Analysis of the Hessian of Over-Parametrized Neural Networks (2017) — 516 citations
- A Generative Process for Contractive Auto-Encoders (2012) — 51 citations
- Higher Order Contractive Auto-Encoder (2011) — 283 citations
- On the saddle point problem for non-convex optimization (2014) — 117 citations
- Large-Scale Learning of Embeddings with Reconstruction Sampling (2011) — 42 citations
- Combining modality specific deep neural networks for emotion recognition in video (2013) — 397 citations
- Big Neural Networks Waste Capacity (2013) — 87 citations