Le Song
Artificial Intelligence · AAAI Conference on Artificial Intelligence · 2007–2020
A researcher in the Science corpus: 81 papers; trusts 2,674 researchers and is trusted by 2,325 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,191 citations into it; #593 of 36,961 by trust here, #717 by citations
- Computer Vision and Pattern Recognition — 505 citations into it; #2,207 of 21,973 by trust here, #1,326 by citations
- Statistics and Probability — 258 citations into it; #685 of 13,188 by trust here, #529 by citations
- Statistical Learning Theory — 221 citations into it; #170 of 1,040 by trust here, #129 by citations
- Optimization & Training — 216 citations into it; #1,495 of 2,605 by trust here, #999 by citations
- Probabilistic & Bayesian Methods — 173 citations into it; #109 of 1,526 by trust here, #82 by citations
- Natural Language Processing — 162 citations into it; #5,064 of 5,725 by trust here, #2,867 by citations
- Representation & Self-Supervised Learning — 157 citations into it; #354 of 3,156 by trust here, #470 by citations
Whom Le Song trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Arthur Gretton
- Bernhard Schölkopf
- Kenji Fukumizu
- Alex Smola
- Geoffrey E. Hinton
- Michael I. Jordan
- Alex Krizhevsky
- Yoshua Bengio
- Diederik P. Kingma
- Francis R. Bach
Who trusts Le Song overall
- Kenji Fukumizu
- Krikamol Muandet
- Arthur Gretton
- Yu Nishiyama
- Bernhard Schölkopf
- Motonobu Kanagawa
- Bharath K. Sriperumbudur
- Steffen Grünewälder
- Kun Zhang
- Byron Boots
Papers from Le Song's perspective
Ordered by how strongly the researchers Le Song trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- SphereFace: Deep Hypersphere Embedding for Face Recognition (2017) — 3,098 citations
- Deep Fried Convnets (2014) — 274 citations
- A Hilbert Space Embedding for Distributions (2007) — 1,003 citations
- Learning Combinatorial Optimization Algorithms over Graphs (2017) — 1,745 citations
- Discriminative Embeddings of Latent Variable Models for Structured Data (2016) — 757 citations
- Scalable Kernel Methods via Doubly Stochastic Gradients (2014) — 238 citations
- Hilbert Space Embeddings of Hidden Markov Models (2010) — 244 citations
- Hilbert space embeddings of conditional distributions with applications to dynamical systems (2009) — 415 citations
- Variational Reasoning for Question Answering with Knowledge Graph (2017) — 576 citations
- A la Carte - Learning Fast Kernels (2014) — 139 citations
- Learning to Explain: An Information-Theoretic Perspective on Model Interpretation (2018) — 666 citations
- Supervised feature selection via dependence estimation (2007) — 410 citations
- Diverse Neural Network Learns True Target Functions (2016) — 147 citations
- Exponential Family Estimation via Adversarial Dynamics Embedding (2019) — 58 citations
- Feature Selection via Dependence Maximization (2012) — 477 citations
- Syntax-Directed Variational Autoencoder for Structured Data (2018) — 358 citations
- Learning to Branch in Mixed Integer Programming (2016) — 434 citations
- Boosting the Actor with Dual Critic (2017) — 46 citations
- Deep Hyperspherical Learning (2017) — 153 citations
- Kernel Belief Propagation (2011) — 86 citations