Greg Ver Steeg

Artificial Intelligence · 2007–2021

A researcher in the Science corpus: 17 papers; trusts 300 researchers and is trusted by 35 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 189 citations into it; #5,946 of 35,345 by trust here, #6,468 by citations
• Computer Vision and Pattern Recognition — 83 citations into it; #14,396 of 21,575 by trust here, #11,950 by citations
• Statistical and Nonlinear Physics — 67 citations into it; #5,419 of 10,127 by trust here, #4,281 by citations
• Representation & Self-Supervised Learning — 56 citations into it; #3,025 of 3,145 by trust here, #2,404 by citations
• Safety, Robustness & Interpretability — 45 citations into it; #1,609 of 2,251 by trust here, #1,731 by citations
• Optimization & Training — 34 citations into it
• Safety Research — 25 citations into it
• Generative Models — 23 citations into it

Whom Greg Ver Steeg trusts overall

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

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Alex Krizhevsky
5. Yann LeCun
6. Michael I. Jordan
7. Kaiming He
8. Ilya Sutskever
9. Radford M. Neal
10. Max Welling

Who trusts Greg Ver Steeg overall

1. Kristina Lerman
2. Alberto Quattrini Li
3. Fei Ye
4. F. Sahli Costabal
5. Shuyang Gao
6. T. Chen
7. Adar Elad
8. Weihao Gao
9. Grant Salton
10. Ninareh Mehrabi

Papers from Greg Ver Steeg's perspective

Ordered by how strongly the researchers Greg Ver Steeg 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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Invariant Representations without Adversarial Training (2018) — 250 citations
• Variational Information Maximization for Feature Selection (2016) — 53 citations
• Improving Generalization by Controlling Label-Noise Information in Neural Network Weights (2020) — 61 citations
• What Stops Social Epidemics? (2011) — 98 citations
• Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation (2021) — 80 citations
• Attributing Fair Decisions with Attention Interventions (2021) — 23 citations
• Invariant Representations through Adversarial Forgetting (2019) — 47 citations
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing (2019) — 1,157 citations
• Auto-Encoding Total Correlation Explanation (2018) — 84 citations
• Evading the Adversary in Invariant Representation (2018) — 7 citations
• P4ML: A Phased Performance-Based Pipeline Planner for Automated Machine Learning (2018)
• Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledge (2016) — 191 citations
• Latent Space Model for Multi-Modal Social Data (2015) — 22 citations
• Maximally Informative Hierarchical Representations of High-Dimensional Data (2014) — 70 citations
• Non-parametric Entropy Estimation Toolbox (NPEET) (2014)
• Scalable Temporal Latent Space Inference for Link Prediction in Dynamic Social Networks (2014) — 210 citations
• Entangling Power of an Expanding Universe (2007) — 183 citations