Sepp Hochreiter
Artificial Intelligence · 1994–2024
A researcher in the Science corpus: 49 papers; trusts 1,632 researchers and is trusted by 21,467 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 810 citations into it; #23 of 36,961 by trust here, #60 by citations
- Computer Vision and Pattern Recognition — 367 citations into it; #928 of 21,973 by trust here, #1,234 by citations
- Model Architectures — 182 citations into it; #11 of 2,288 by trust here, #19 by citations
- Molecular Biology — 172 citations into it; #1,584 of 17,836 by trust here, #2,411 by citations
- Optimization & Training — 164 citations into it; #56 of 2,605 by trust here, #28 by citations
- Computational Theory and Mathematics — 163 citations into it; #1,710 of 12,489 by trust here, #433 by citations
- Reinforcement Learning — 152 citations into it; #574 of 2,250 by trust here, #797 by citations
- Representation & Self-Supervised Learning — 120 citations into it; #982 of 3,156 by trust here, #1,845 by citations
Whom Sepp Hochreiter trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- J. Urgen Schmidhuber
- Geoffrey E. Hinton
- Yoshua Bengio
- David John Cameron MacKay
- Alex Krizhevsky
- Yann LeCun
- Ronald J. Williams
- Barak A. Pearlmutter
- Diederik P. Kingma
- Michael C. Mozer
Who trusts Sepp Hochreiter overall
- Yoshua Bengio
- J. Urgen Schmidhuber
- Quoc V. Le
- Zhe Gan
- Mohit Bansal
- Kyunghyun Cho
- Sergey Levine
- Ruslan Salakhutdinov
- Trevor Darrell
- Percy Liang
Papers from Sepp Hochreiter's perspective
Ordered by how strongly the researchers Sepp Hochreiter 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)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- 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)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Long Short-Term Memory (1997)
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) (2015) — 6,140 citations
- Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies (2001) — 2,083 citations
- Flat Minima (1997)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium (2017) — 506 citations
- Learning to Learn Using Gradient Descent (2001) — 339 citations
- Self-Normalizing Neural Networks (2017) — 2,892 citations
- RUDDER: Return Decomposition for Delayed Rewards (2018) — 277 citations
- The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions (1998)
- LSTM can Solve Hard Long Time Lag Problems (1996)
- Meta-learning with backpropagation (2001) — 62 citations
- Feature Extraction Through LOCOCODE (1999)
- Hopfield Networks is All You Need (2020) — 701 citations
- Simplifying Neural Nets by Discovering Flat Minima (1994)
- Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields (2017) — 81 citations
- CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (2021) — 129 citations
- Guessing can Outperform Many Long Time Lag Algorithms (1996)
- Rectified Factor Networks (2015) — 17 citations
- Explaining and Interpreting LSTMs (2019) — 89 citations
- Optimal kernels for unsupervised learning (2005) — 5 citations