Samy Bengio
Artificial Intelligence · 1991–2025
A researcher in the Science corpus: 76 papers; trusts 3,409 researchers and is trusted by 21,585 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,369 citations into it; #43 of 36,961 by trust here, #62 by citations
- Computer Vision and Pattern Recognition — 782 citations into it; #129 of 21,973 by trust here, #114 by citations
- Natural Language Processing — 316 citations into it; #137 of 5,725 by trust here, #113 by citations
- Model Architectures — 277 citations into it; #146 of 2,288 by trust here, #176 by citations
- Optimization & Training — 225 citations into it; #437 of 2,605 by trust here, #378 by citations
- Signal Processing — 159 citations into it; #72 of 7,592 by trust here, #72 by citations
- Representation & Self-Supervised Learning — 155 citations into it; #272 of 3,156 by trust here, #183 by citations
- Generative Models — 106 citations into it; #59 of 1,963 by trust here, #88 by citations
Whom Samy Bengio trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Alex Krizhevsky
- Ilya Sutskever
- Diederik P. Kingma
- Kaiming He
- Alex Graves
- Christian Szegedy
- Yann LeCun
- Oriol Vinyals
Who trusts Samy Bengio overall
- Yoshua Bengio
- Sergey Levine
- Quoc V. Le
- Zhe Gan
- Chelsea Finn
- Mohit Bansal
- Trevor Darrell
- Ruslan Salakhutdinov
- Zeynep Akata
- Kyunghyun Cho
Papers from Samy Bengio's perspective
Ordered by how strongly the researchers Samy Bengio 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)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Show and tell: A neural image caption generator (2014) — 6,597 citations
- DeViSE: A Deep Visual-Semantic Embedding Model (2013) — 3,053 citations
- Understanding deep learning requires rethinking generalization (2016) — 5,191 citations
- Generating Sentences from a Continuous Space (2015) — 2,543 citations
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks (2015) — 2,414 citations
- Density estimation using Real NVP (2016) — 4,503 citations
- Zero-Shot Learning by Convex Combination of Semantic Embeddings (2013) — 981 citations
- Adversarial examples in the physical world (2016) — 6,799 citations
- Large scale image annotation: learning to rank with joint word-image embeddings (2010) — 461 citations
- Reward Augmented Maximum Likelihood for Neural Structured Prediction (2016) — 269 citations
- Tensor2Tensor for Neural Machine Translation (2018) — 553 citations
- Adversarial Machine Learning at Scale (2016) — 3,411 citations
- Learning a synaptic learning rule (1991)
- Large Scale Online Learning of Image Similarity Through Ranking (2009) — 917 citations
- Order Matters: Sequence to sequence for sets (2015) — 1,043 citations
- Neural Combinatorial Optimization with Reinforcement Learning (2016) — 1,854 citations
- Modeling High-Dimensional Discrete Data with Multi-Layer Neural Networks (1999)
- On the Optimization of a Synaptic Learning Rule (2007) — 293 citations
- A Study on Overfitting in Deep Reinforcement Learning (2018) — 437 citations
- Sharp Minima Can Generalize For Deep Nets (2017) — 918 citations