Frederik Kunstner
Artificial Intelligence · 2018–2019
A researcher in the Science corpus: 3 papers; trusts 64 researchers and is trusted by 21 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 56 citations into it; #8,842 of 35,345 by trust here, #17,776 by citations
- Optimization & Training — 53 citations into it; #1,112 of 2,601 by trust here, #1,904 by citations
- Computer Vision and Pattern Recognition — 19 citations into it
- Probabilistic & Bayesian Methods — 18 citations into it
- Statistics and Probability — 10 citations into it
- Statistical and Nonlinear Physics — 8 citations into it
- Model Architectures — 7 citations into it
- Signal Processing — 7 citations into it
Whom Frederik Kunstner trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- James Martens
- Shun-ichi Amari
- Alex Graves
- Diederik P. Kingma
- N. Schraudolph
- Yoshua Bengio
- Geoffrey E. Hinton
- Yann LeCun
- Jimmy Ba
- Alex Krizhevsky
Who trusts Frederik Kunstner overall
- Reinhard Heckel
- Sidak Pal Singh
- Piotr A. Sokól
- Dan Alistarh
- Erik A. Daxberger
- Agustinus Kristiadi
- Elias Frantar
- Yi-Lin Sung
- Felix Dangel
- Apoorva Sharma
Papers from Frederik Kunstner's perspective
Ordered by how strongly the researchers Frederik Kunstner 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)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet: A large-scale hierarchical image database
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Limitations of the Empirical Fisher Approximation (2019) — 290 citations
- BackPACK: Packing more into backprop (2019) — 117 citations
- SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient (2018) — 67 citations