Luke Metz
Artificial Intelligence · 2015–2022
A researcher in the Science corpus: 13 papers; trusts 1,539 researchers and is trusted by 12,172 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 362 citations into it; #304 of 36,961 by trust here, #383 by citations
- Computer Vision and Pattern Recognition — 199 citations into it; #228 of 21,973 by trust here, #294 by citations
- Optimization & Training — 129 citations into it; #2,006 of 2,605 by trust here, #1,718 by citations
- Reinforcement Learning — 90 citations into it; #1,448 of 2,250 by trust here, #1,589 by citations
- Generative Models — 78 citations into it; #16 of 1,963 by trust here, #31 by citations
- Representation & Self-Supervised Learning — 55 citations into it
- Model Architectures — 54 citations into it; #1,761 of 2,288 by trust here, #1,731 by citations
- Management Science and Operations Research — 47 citations into it
Whom Luke Metz trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Diederik P. Kingma
- Geoffrey E. Hinton
- Alex Krizhevsky
- J. Urgen Schmidhuber
- Ronald J. Williams
- Yann LeCun
- Ilya Sutskever
- Sepp Hochreiter
- Kaiming He
Who trusts Luke Metz overall
- Yoshua Bengio
- Zhe Gan
- Sergey Levine
- Dacheng Tao
- Bernt Schiele
- Ngoc-Trung Tran
- Jun-Yan Zhu
- Chunyuan Li
- Andrea Vedaldi
- Luc Van Gool
Papers from Luke Metz's perspective
Ordered by how strongly the researchers Luke Metz 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- 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
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (2015) — 15,179 citations
- Unrolled Generative Adversarial Networks (2016) — 1,076 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- BEGAN: Boundary Equilibrium Generative Adversarial Networks (2017) — 1,207 citations
- Discrete Sequential Prediction of Continuous Actions for Deep RL (2017) — 135 citations
- Adversarial Spheres (2018) — 358 citations
- Meta-Learning Update Rules for Unsupervised Representation Learning (2018) — 132 citations
- Understanding and correcting pathologies in the training of learned optimizers (2018) — 168 citations
- On Linear Identifiability of Learned Representations (2020) — 115 citations
- Learning an Adaptive Learning Rate Schedule (2019) — 79 citations
- Gradients are Not All You Need (2021) — 111 citations
- Practical tradeoffs between memory, compute, and performance in learned optimizers (2022) — 42 citations
- Learning to Predict Without Looking Ahead: World Models Without Forward Prediction (2019) — 39 citations