Ben Edwards

Artificial Intelligence · 2018

A researcher in the Science corpus: 4 papers; trusts 38 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 102 citations into it
• Safety, Robustness & Interpretability — 94 citations into it
• Computer Vision and Pattern Recognition — 37 citations into it
• Model Architectures — 6 citations into it
• Representation & Self-Supervised Learning — 5 citations into it

Whom Ben Edwards trusts overall

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

1. Alex Krizhevsky
2. Diederik P. Kingma
3. Yann LeCun
4. Geoffrey E. Hinton
5. Nicolas Papernot
6. Yoshua Bengio
7. François Chollet
8. Ian J. Goodfellow
9. Christian Szegedy
10. Jimmy Ba

Who trusts Ben Edwards overall

1. Matthew Jagielski
2. Tribhuvanesh Orekondy

Papers from Ben Edwards's perspective

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

Their papers

• Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering (2018) — 980 citations
• Adversarial Robustness Toolbox v1.0.0 (2018) — 573 citations
• Defending Against Model Stealing Attacks Using Deceptive Perturbations (2018) — 47 citations
• Adversarial Robustness Toolbox v0.2.2 (2018) — 59 citations