Roman Garnett
Artificial Intelligence · 2005–2019
A researcher in the Science corpus: 14 papers; trusts 282 researchers and is trusted by 111 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 148 citations into it; #3,140 of 36,961 by trust here, #5,392 by citations
- Computer Vision and Pattern Recognition — 51 citations into it; #9,075 of 21,973 by trust here, #13,584 by citations
- Computational Theory and Mathematics — 48 citations into it; #3,630 of 12,489 by trust here, #3,972 by citations
- Probabilistic & Bayesian Methods — 45 citations into it; #320 of 1,526 by trust here, #443 by citations
- Graph Learning — 37 citations into it; #299 of 700 by trust here, #418 by citations
- Statistics and Probability — 30 citations into it; #1,239 of 13,188 by trust here, #1,757 by citations
- Generative Models — 17 citations into it
- Model Architectures — 14 citations into it
Whom Roman Garnett trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Radford M. Neal
- David John Cameron MacKay
- Carl E. Rasmussen
- Donald R. Jones
- Frank Hutter
- Zoubin Ghahramani
- Geoffrey E. Hinton
- Yoshua Bengio
- Robert Tibshirani
- Alex Krizhevsky
Who trusts Roman Garnett overall
- Michael A. Osborne
- Bobak Shahriari
- Ziyun Wang
- Roberto Calandra
- Nando de Freitas
- Kevin Swersky
- Peter I. Frazier
- Eric Brochu
- Jasper Snoek
- Stephen J. Roberts
Papers from Roman Garnett's perspective
Ordered by how strongly the researchers Roman Garnett 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)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Bayesian dark knowledge (2015) — 271 citations
- Bayesian optimization for sensor set selection (2010) — 178 citations
- Sequential Bayesian Prediction in the Presence of Changepoints and Faults (2010) — 79 citations
- D-VAE: A Variational Autoencoder for Directed Acyclic Graphs (2019) — 238 citations
- Active Learning of Linear Embeddings for Gaussian Processes (2013) — 104 citations
- Efficient Graph Kernels by Randomization (2012) — 66 citations
- Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature (2014) — 121 citations
- Power Iterated Color Refinement (2014) — 41 citations
- Anomaly Detection and Removal Using Non-Stationary Gaussian Processes (2015) — 11 citations
- Differentially Private Learning of Structured Discrete Distributions (2015)
- Propagation kernels: efficient graph kernels from propagated information (2014) — 303 citations
- Active Learning of Model Evidence Using Bayesian Quadrature (2012) — 138 citations
- Gaussian Processes for Global Optimization (2008)
- A universal noise removal algorithm with an impulse detector (2005) — 630 citations