Wonsung Lee

Artificial Intelligence · 2017–2019

A researcher in the Science corpus: 2 papers; trusts 67 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 39 citations into it
• Computer Vision and Pattern Recognition — 29 citations into it
• Generative Models — 22 citations into it
• Probabilistic & Bayesian Methods — 17 citations into it
• Information Systems — 13 citations into it
• Representation & Self-Supervised Learning — 13 citations into it
• Recommender Systems — 10 citations into it
• Natural Language Processing — 8 citations into it

Whom Wonsung Lee trusts overall

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

1. Diederik P. Kingma
2. Ruslan Salakhutdinov
3. Geoffrey E. Hinton
4. Shakir Mohamed
5. Yoshua Bengio
6. Danilo Jimenez Rezende
7. Alex Krizhevsky
8. Max Welling
9. Hugo Larochelle
10. Radford M. Neal

Papers from Wonsung Lee's perspective

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

Their papers

• Dirichlet Variational Autoencoder (2019) — 123 citations
• Augmented Variational Autoencoders for Collaborative Filtering with Auxiliary Information (2017) — 70 citations