Ji Gao

Artificial Intelligence · with Qi · 2016–2018

A researcher in the Science corpus: 2 papers; trusts 119 researchers and is trusted by 5 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 60 citations into it; #21,358 of 35,345 by trust here, #14,438 by citations
• Safety, Robustness & Interpretability — 49 citations into it; #1,402 of 2,251 by trust here, #1,371 by citations
• Computer Vision and Pattern Recognition — 24 citations into it
• Signal Processing — 13 citations into it; #4,403 of 7,572 by trust here, #2,221 by citations
• Computer Networks and Communications — 12 citations into it
• Natural Language Processing — 12 citations into it
• Model Architectures — 8 citations into it
• Representation & Self-Supervised Learning — 8 citations into it

Whom Ji Gao trusts overall

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

1. Ian J. Goodfellow
2. Nicolas Papernot
3. Alex Krizhevsky
4. Yann LeCun
5. Geoffrey E. Hinton
6. Yoshua Bengio
7. Christian Szegedy
8. Richard Socher
9. Ilya Sutskever
10. Nicholas Carlini

Who trusts Ji Gao overall

1. Yonatan Belinkov
2. Siddhant Garg
3. Di Jin
4. W. Zhang
5. Shuhuai Ren
6. Nadir Durrani
7. Linyang Li
8. Minhao Cheng
9. Jinfeng Li
10. Puyudi Yang

Papers from Ji Gao's perspective

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

Their papers

• Black-Box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers (2018) — 869 citations
• A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples (2016) — 31 citations