James Martens
Artificial Intelligence · 2010–2019
A researcher in the Science corpus: 20 papers; trusts 1,266 researchers and is trusted by 16,404 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 445 citations into it; #40 of 36,961 by trust here, #468 by citations
- Optimization & Training — 285 citations into it; #17 of 2,605 by trust here, #40 by citations
- Computer Vision and Pattern Recognition — 124 citations into it; #1,149 of 21,973 by trust here, #2,336 by citations
- Model Architectures — 93 citations into it
- Computational Theory and Mathematics — 66 citations into it; #11,798 of 12,489 by trust here, #9,569 by citations
- Signal Processing — 61 citations into it
- Management Science and Operations Research — 60 citations into it; #6,725 of 12,201 by trust here, #3,426 by citations
- Computational Mechanics — 58 citations into it; #152 of 10,021 by trust here, #1,515 by citations
Whom James Martens trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Shun-ichi Amari
- Yoshua Bengio
- Yann LeCun
- Geoffrey E. Hinton
- Ilya Sutskever
- Sepp Hochreiter
- Alex Krizhevsky
- N. Schraudolph
- Oriol Vinyals
- Radford M. Neal
Who trusts James Martens overall
- Yoshua Bengio
- Roger Baker Grosse
- Guodong Zhang
- Ilya Sutskever
- Quoc V. Le
- Ruslan Salakhutdinov
- Li Deng
- Sergey Levine
- Kyunghyun Cho
- Razvan Pascanu
Papers from James Martens's perspective
Ordered by how strongly the researchers James Martens 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
- 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
- On the importance of initialization and momentum in deep learning (2013) — 5,312 citations
- Generating Text with Recurrent Neural Networks (2011) — 1,560 citations
- Deep learning via Hessian-free optimization (2010) — 1,146 citations
- Optimizing Neural Networks with Kronecker-factored Approximate Curvature (2015) — 1,395 citations
- Learning Recurrent Neural Networks with Hessian-Free Optimization (2011) — 658 citations
- Adding Gradient Noise Improves Learning for Very Deep Networks (2015) — 597 citations
- New Insights and Perspectives on the Natural Gradient Method (2014) — 832 citations
- Training Deep and Recurrent Networks with Hessian-Free Optimization (2012) — 259 citations
- The Mechanics of n-Player Differentiable Games (2018) — 315 citations
- Adversarial Robustness through Local Linearization (2019) — 333 citations
- A Kronecker-factored approximate Fisher matrix for convolution layers (2016) — 317 citations
- Estimating the Hessian by Back-propagating Curvature (2012) — 87 citations
- Distributed Second-Order Optimization using Kronecker-Factored Approximations (2016) — 126 citations
- Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model (2019) — 192 citations
- New perspectives on the natural gradient method (2014) — 78 citations
- Differentiable Game Mechanics (2019) — 95 citations
- On the Expressive Efficiency of Sum Product Networks (2014) — 75 citations
- Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks (2019) — 139 citations
- Kronecker-factored Curvature Approximations for Recurrent Neural Networks (2018) — 106 citations
- Second-order Optimization for Neural Networks (2016) — 67 citations