HyoukJoong Lee

Artificial Intelligence · 2018–2021

A researcher in the Science corpus: 7 papers; trusts 119 researchers and is trusted by 17 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 147 citations into it; #35,097 of 35,345 by trust here, #3,757 by citations
• Computer Vision and Pattern Recognition — 114 citations into it; #8,842 of 21,575 by trust here, #2,207 by citations
• Optimization & Training — 59 citations into it; #1,907 of 2,601 by trust here, #395 by citations
• Model Architectures — 50 citations into it
• Natural Language Processing — 47 citations into it
• Hardware and Architecture — 33 citations into it; #1,215 of 1,551 by trust here, #101 by citations
• ML Systems & Hardware — 20 citations into it
• Statistical and Nonlinear Physics — 9 citations into it

Whom HyoukJoong Lee trusts overall

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

1. Noam Shazeer
2. Alex Krizhevsky
3. Geoffrey E. Hinton
4. Diederik P. Kingma
5. Kaiming He
6. Ilya Sutskever
7. Yoshua Bengio
8. Ashish Vaswani
9. Yann LeCun
10. Jimmy Ba

Who trusts HyoukJoong Lee overall

1. Yi Tay
2. Hieu Pham
3. Jiahui Yu
4. Barret Zoph
5. Samyam Rajbhandari
6. Ankur Bapna
7. Zihang Dai
8. Mostafa Dehghani
9. Yuanzhong Xu
10. Joan Puigcerver

Papers from HyoukJoong Lee's perspective

Ordered by how strongly the researchers HyoukJoong Lee trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
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. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. ImageNet Large Scale Visual Recognition Challenge
9. Going deeper with convolutions
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding (2020) — 2,182 citations
• GSPMD: General and Scalable Parallelization for ML Computation Graphs (2021) — 188 citations
• Mesh-TensorFlow: Deep Learning for Supercomputers (2018) — 439 citations
• Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
• Automatic Cross-Replica Sharding of Weight Update in Data-Parallel Training (2020) — 52 citations
• Scale MLPerf-0.6 models on Google TPU-v3 Pods (2019) — 43 citations
• GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism (2018) — 2,195 citations