Asja Fischer
Artificial Intelligence · 2012–2020
A researcher in the Science corpus: 13 papers; trusts 673 researchers and is trusted by 47 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 186 citations into it; #6,504 of 35,345 by trust here, #3,215 by citations
- Computer Vision and Pattern Recognition — 167 citations into it; #4,268 of 21,575 by trust here, #4,623 by citations
- Probabilistic & Bayesian Methods — 121 citations into it
- Optimization & Training — 90 citations into it; #1,446 of 2,601 by trust here, #730 by citations
- Generative Models — 60 citations into it
- Model Architectures — 45 citations into it
- Representation & Self-Supervised Learning — 45 citations into it
- Statistical and Nonlinear Physics — 41 citations into it; #2,311 of 10,127 by trust here, #4,281 by citations
Whom Asja Fischer trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Radford M. Neal
- Ruslan Salakhutdinov
- Tijmen Tieleman
- Shun-ichi Amari
- David John Cameron MacKay
- Aaron C. Courville
- Yann LeCun
- Diederik P. Kingma
Who trusts Asja Fischer overall
- Mufti Mahmud
- S. Ji
- Aminu Da’u
- Qiubin Liang
- Jérôme Tubiana
- Youbiao He
- M. S. Kaiser
- Ngoc-Trung Tran
- Lasse Borgholt
- Cristian Bodnar
Papers from Asja Fischer's perspective
Ordered by how strongly the researchers Asja Fischer 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
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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
- A Closer Look at Memorization in Deep Networks (2017) — 2,230 citations
- Difference Target Propagation (2014) — 422 citations
- Leveraging Frequency Analysis for Deep Fake Image Recognition (2020) — 943 citations
- On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length (2018) — 145 citations
- Bidirectional Helmholtz Machines (2015) — 26 citations
- Training restricted Boltzmann machines: An introduction (2014) — 510 citations
- Three Factors Influencing Minima in SGD (2017) — 546 citations
- The flip-the-state transition operator for restricted Boltzmann machines (2013) — 22 citations
- On the regularization of Wasserstein GANs (2017) — 221 citations
- Training Restricted Boltzmann Machines (2015) — 40 citations
- An objective function for STDP (2015) — 14 citations
- Approximation properties of DBNs with binary hidden units and real-valued visible units (2013) — 10 citations
- An Introduction to Restricted Boltzmann Machines (2012) — 638 citations