Moustapha Cissé
Artificial Intelligence · 2011–2018
A researcher in the Science corpus: 11 papers; trusts 1,326 researchers and is trusted by 4,395 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 312 citations into it; #664 of 36,961 by trust here, #864 by citations
- Computer Vision and Pattern Recognition — 142 citations into it; #781 of 21,973 by trust here, #911 by citations
- Safety, Robustness & Interpretability — 86 citations into it; #153 of 2,259 by trust here, #197 by citations
- Natural Language Processing — 75 citations into it; #3,760 of 5,725 by trust here, #4,392 by citations
- Model Architectures — 58 citations into it
- Optimization & Training — 43 citations into it; #193 of 2,605 by trust here, #137 by citations
- Signal Processing — 34 citations into it; #5,664 of 7,592 by trust here, #2,523 by citations
- Representation & Self-Supervised Learning — 32 citations into it
Whom Moustapha Cissé trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Yoshua Bengio
- Christian Szegedy
- Yann LeCun
- Diederik P. Kingma
- Ian J. Goodfellow
- Ilya Sutskever
- Tomas Mikolov
Who trusts Moustapha Cissé overall
- Nicholas Carlini
- Yoshua Bengio
- Ekin Dogus Cubuk
- Quoc V. Le
- Nicolas Papernot
- Bo Li
- Yang Song
- Barret Zoph
- Lu Jiang
- Alan L. Yuille
Papers from Moustapha Cissé's perspective
Ordered by how strongly the researchers Moustapha Cissé 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- mixup: Beyond Empirical Risk Minimization (2017) — 12,076 citations
- Efficient softmax approximation for GPUs (2016) — 297 citations
- Parseval Networks: Improving Robustness to Adversarial Examples (2017) — 896 citations
- Countering Adversarial Images using Input Transformations (2018) — 1,638 citations
- ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases (2017) — 180 citations
- ConvNets and ImageNet Beyond Accuracy: Explanations, Bias Detection, Adversarial Examples and Model Criticism (2017) — 48 citations
- Unbounded cache model for online language modeling with open vocabulary (2017) — 78 citations
- Houdini: Fooling Deep Structured Prediction Models (2017) — 280 citations
- Deep Learners Benefit More from Out-of-Distribution Examples (2011) — 169 citations
- Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring (2018) — 872 citations
- Is Attribute-Based Zero-Shot Learning an Ill-Posed Strategy? (2016) — 8 citations