Taesik Na

Artificial Intelligence · 2017

A researcher in the Science corpus: 2 papers; trusts 19 researchers and is trusted by 3 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 19 citations into it; #25,803 of 35,345 by trust here, #21,878 by citations
• Computer Vision and Pattern Recognition — 10 citations into it; #21,173 of 21,575 by trust here, #18,782 by citations
• Safety, Robustness & Interpretability — 10 citations into it
• Model Architectures — 8 citations into it

Whom Taesik Na trusts overall

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

1. Alex Krizhevsky
2. Ian J. Goodfellow
3. Alexey Kurakin
4. Christian Szegedy
5. Kaiming He
6. Sergey Ioffe
7. Geoffrey E. Hinton
8. Yoshua Bengio
9. H. T. Kung
10. Ilya Sutskever

Who trusts Taesik Na overall

1. Naveed Akhtar
2. Sebastian U. Stich
3. Ho Bae
4. Runqi Wang
5. Runtian Zhai
6. Joachim Ott
7. Ajmal Saeed Mian
8. Samuel Horváth
9. Jaehee Jang
10. Yuxiang Bao

Papers from Taesik Na's perspective

Ordered by how strongly the researchers Taesik Na 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. Long Short-Term Memory
5. Gradient-based learning applied to document recognition
6. ImageNet: A large-scale hierarchical image database
7. Learning Multiple Layers of Features from Tiny Images
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Attention is All you Need (Neural Information Processing Systems)
10. Going deeper with convolutions

Their papers

• Cascade Adversarial Machine Learning Regularized with a Unified Embedding (2017) — 107 citations
• On-chip training of recurrent neural networks with limited numerical precision (2017) — 42 citations