James Townsend
Computer Vision and Pattern Recognition · 2016–2019
A researcher in the Science corpus: 3 papers; trusts 64 researchers and is trusted by 20 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 26 citations into it; #6,301 of 21,575 by trust here, #12,419 by citations
- Artificial Intelligence — 19 citations into it; #8,905 of 35,345 by trust here, #18,586 by citations
- Generative Models — 19 citations into it; #1,562 of 1,956 by trust here, #1,748 by citations
- Efficiency & Compression — 10 citations into it
- Information Theory — 8 citations into it; #161 of 196 by trust here, #169 by citations
- Probabilistic & Bayesian Methods — 8 citations into it; #901 of 1,525 by trust here, #1,075 by citations
- Signal Processing — 6 citations into it; #3,508 of 7,572 by trust here, #4,373 by citations
- Computational Theory and Mathematics — 5 citations into it
Whom James Townsend trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Chris S. Wallace
- Danilo Jimenez Rezende
- Yann LeCun
- Yoshua Bengio
- Max Welling
- Brendan J. Frey
- Radford M. Neal
- Aäron van den Oord
Who trusts James Townsend overall
- Shifeng Zhang
- Yibo Yang
- Jonathan Ho
- Zhihao Duan
- F. Kingma
- Ning Kang
- Diederik P. Kingma
- Pieter Abbeel
- Emiel Hoogeboom
- Robert Bamler
Papers from James Townsend's perspective
Ordered by how strongly the researchers James Townsend trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- 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
- Practical Lossless Compression with Latent Variables using Bits Back Coding (2019) — 161 citations
- HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models (2019) — 61 citations
- Pymanopt: A Python Toolbox for Optimization on Manifolds using Automatic Differentiation (2016) — 309 citations