David Barber
Artificial Intelligence · 1997–2020
A researcher in the Science corpus: 27 papers; trusts 1,312 researchers and is trusted by 2,301 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 359 citations into it; #573 of 36,961 by trust here, #2,164 by citations
- Computer Vision and Pattern Recognition — 136 citations into it; #2,431 of 21,973 by trust here, #3,050 by citations
- Probabilistic & Bayesian Methods — 124 citations into it; #137 of 1,526 by trust here, #206 by citations
- Optimization & Training — 73 citations into it; #462 of 2,605 by trust here, #961 by citations
- Generative Models — 60 citations into it; #1,567 of 1,963 by trust here, #1,656 by citations
- Statistics and Probability — 57 citations into it; #1,089 of 13,188 by trust here, #2,412 by citations
- Model Architectures — 39 citations into it; #1,048 of 2,288 by trust here, #1,731 by citations
- Representation & Self-Supervised Learning — 33 citations into it; #436 of 3,156 by trust here, #849 by citations
Whom David Barber trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- David John Cameron MacKay
- Radford M. Neal
- Geoffrey E. Hinton
- Diederik P. Kingma
- Michael I. Jordan
- Tommi S. Jaakkola
- Yoshua Bengio
- Alex Krizhevsky
- Yann LeCun
- Charles M. Bishop
Who trusts David Barber overall
- Yarin Gal
- Yoshua Bengio
- Matthias W. Seeger
- Edward Challis
- Kyunghyun Cho
- David M. Blei
- Zoubin Ghahramani
- Sergey Levine
- Yingzhen Li
- Manfred Opper
Papers from David Barber's perspective
Ordered by how strongly the researchers David Barber 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)
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- 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
- Thinking Fast and Slow with Deep Learning and Tree Search (2017) — 481 citations
- The IM algorithm: a variational approach to Information Maximization (2003) — 535 citations
- Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting (2018) — 384 citations
- Modular Networks: Learning to Decompose Neural Computation (2018) — 127 citations
- An Auxiliary Variational Method (2004) — 75 citations
- Bayesian reasoning and machine learning (2012) — 1,627 citations
- Practical Lossless Compression with Latent Variables using Bits Back Coding (2019) — 161 citations
- A Scalable Laplace Approximation for Neural Networks (2018) — 513 citations
- Ensemble learning in Bayesian neural networks (1998)
- Affine Independent Variational Inference (2012) — 20 citations
- Information Maximization in Noisy Channels : A Variational Approach (2003) — 40 citations
- Practical Gauss-Newton Optimisation for Deep Learning (2017) — 266 citations
- Generating Sentences Using a Dynamic Canvas (2018) — 8 citations
- Complementary Sum Sampling for Likelihood Approximation in Large Scale Classification (2017) — 28 citations
- Gaussian Kullback-Leibler approximate inference (2013) — 78 citations
- Bayesian Time Series Models (2011) — 113 citations
- HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models (2019) — 61 citations
- Variational Cumulant Expansions for Intractable Distributions (2011) — 15 citations
- On the Computational Complexity of Stochastic Controller Optimization in POMDPs (2011) — 92 citations
- Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks (2020) — 10 citations