R. Caruana
Artificial Intelligence · Journal of Advances in Modeling Earth Systems · 1993–2020
A researcher in the Science corpus: 48 papers; trusts 892 researchers and is trusted by 12,736 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 538 citations into it; #65 of 36,961 by trust here, #209 by citations
- Computer Vision and Pattern Recognition — 138 citations into it; #966 of 21,973 by trust here, #1,127 by citations
- Statistics and Probability — 123 citations into it; #783 of 13,188 by trust here, #1,469 by citations
- Safety, Robustness & Interpretability — 122 citations into it; #137 of 2,259 by trust here, #216 by citations
- Model Architectures — 79 citations into it; #105 of 2,288 by trust here, #214 by citations
- Information Systems — 71 citations into it; #244 of 9,233 by trust here, #530 by citations
- Optimization & Training — 68 citations into it; #294 of 2,605 by trust here, #408 by citations
- Natural Language Processing — 64 citations into it; #1,489 of 5,725 by trust here, #3,213 by citations
Whom R. Caruana trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Sebastian Thrun
- Geoffrey E. Hinton
- Jerome H. Friedman
- Leo Breiman
- J. Platt
- Trevor J. Hastie
- Alexandru Niculescu-Mizil
- Yin Lou
- Yoshua Bengio
- Alex Krizhevsky
Who trusts R. Caruana overall
- Sebastian Ruder
- Yoshua Bengio
- Jianfeng Gao
- Yu Zhang
- Sergey Levine
- Trevor Darrell
- Dacheng Tao
- Andrea Vedaldi
- Kyunghyun Cho
- Xiaogang Wang
Papers from R. Caruana's perspective
Ordered by how strongly the researchers R. Caruana trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Multitask Learning (1997)
- Do Deep Nets Really Need to be Deep? (2013) — 2,250 citations
- Model compression (2006) — 2,875 citations
- Learning Many Related Tasks at the Same Time with Backpropagation (1994)
- Multitask Learning: A Knowledge-Based Source of Inductive Bias (1993)
- Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission (2015) — 1,942 citations
- Predicting good probabilities with supervised learning (2005) — 2,099 citations
- Ensemble selection from libraries of models (2004) — 1,036 citations
- Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping (2000) — 1,197 citations
- An empirical comparison of supervised learning algorithms (2006) — 2,894 citations
- An empirical evaluation of supervised learning in high dimensions (2008) — 593 citations
- Getting the Most Out of Ensemble Selection (2006) — 170 citations
- Intelligible models for classification and regression (2012) — 575 citations
- Bridging the lexical chasm: statistical approaches to answer-finding (2000) — 361 citations
- Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation (2017) — 212 citations
- Gamut: A Design Probe to Understand How Data Scientists Understand Machine Learning Models (2019) — 281 citations
- Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration (2016) — 160 citations
- Interpretable & Explorable Approximations of Black Box Models (2017) — 259 citations
- Blending LSTMs into CNNs (2015) — 61 citations
- (Not) Bounding the True Error (2001) — 149 citations