Mathias Berglund

Artificial Intelligence · 2013–2016

A researcher in the Science corpus: 6 papers; trusts 93 researchers and is trusted by 368 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 48 citations into it; #2,706 of 35,345 by trust here, #3,261 by citations
• Computer Vision and Pattern Recognition — 41 citations into it; #2,213 of 21,575 by trust here, #2,749 by citations
• Optimization & Training — 32 citations into it
• Representation & Self-Supervised Learning — 19 citations into it; #1,114 of 3,145 by trust here, #613 by citations
• Model Architectures — 18 citations into it; #1,096 of 2,278 by trust here, #1,548 by citations
• Probabilistic & Bayesian Methods — 13 citations into it
• Generative Models — 12 citations into it
• Natural Language Processing — 6 citations into it

Whom Mathias Berglund trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton
2. Yoshua Bengio
3. Yann LeCun
4. Diederik P. Kingma
5. Alex Krizhevsky
6. Kyunghyun Cho
7. Tijmen Tieleman
8. Radford M. Neal
9. Paul Smolensky
10. Ruslan Salakhutdinov

Who trusts Mathias Berglund overall

1. Yoshua Bengio
2. Kyunghyun Cho
3. Klaus Greff
4. J. Urgen Schmidhuber
5. Andriy Mnih
6. Sergey Levine
7. Andrea Vedaldi
8. Sjoerd van Steenkiste
9. Jason Tyler Rolfe
10. Zhe Gan

Papers from Mathias Berglund's perspective

Ordered by how strongly the researchers Mathias Berglund trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Semi-supervised Learning with Ladder Networks (2015) — 1,426 citations
• Techniques for Learning Binary Stochastic Feedforward Neural Networks (2014) — 129 citations
• Tagger: Deep Unsupervised Perceptual Grouping (2016) — 169 citations
• Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters (2015) — 183 citations
• 33rd International Conference on Machine Learning, ICML 2016 (2016) — 10 citations
• Stochastic gradient estimate variance in contrastive divergence and persistent contrastive divergence (2013)