Misha Denil
Artificial Intelligence · 2011–2019
A researcher in the Science corpus: 25 papers; trusts 1,598 researchers and is trusted by 2,554 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 642 citations into it; #792 of 36,961 by trust here, #832 by citations
- Computer Vision and Pattern Recognition — 298 citations into it; #1,298 of 21,973 by trust here, #944 by citations
- Reinforcement Learning — 276 citations into it; #1,630 of 2,250 by trust here, #337 by citations
- Model Architectures — 106 citations into it
- Natural Language Processing — 103 citations into it; #3,970 of 5,725 by trust here, #3,927 by citations
- Optimization & Training — 95 citations into it; #587 of 2,605 by trust here, #153 by citations
- Control and Systems Engineering — 91 citations into it; #7,145 of 8,519 by trust here, #662 by citations
- Management Science and Operations Research — 77 citations into it
Whom Misha Denil trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
- Diederik P. Kingma
- Alex Graves
- Kaiming He
- Karen Simonyan
- Quoc V. Le
Who trusts Misha Denil overall
- Yoshua Bengio
- Gilles Louppe
- Aliaksei Severyn
- Sergey Levine
- Yu Cheng
- Kyunghyun Cho
- Ruslan Salakhutdinov
- Yuxi Li
- Chelsea Finn
- Quoc V. Le
Papers from Misha Denil's perspective
Ordered by how strongly the researchers Misha Denil 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
- 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)
- ImageNet Large Scale Visual Recognition Challenge
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Learning to learn by gradient descent by gradient descent (2016) — 2,222 citations
- Learning to Navigate in Complex Environments (2016) — 958 citations
- Predicting Parameters in Deep Learning (2013) — 1,410 citations
- Deep Fried Convnets (2014) — 274 citations
- Learning Where to Attend with Deep Architectures for Image Tracking (2011) — 210 citations
- Learned Optimizers that Scale and Generalize (2017) — 308 citations
- Programmable Agents (2017) — 43 citations
- Scaling data-driven robotics with reward sketching and batch reinforcement learning (2019) — 160 citations
- Learning to Perform Physics Experiments via Deep Reinforcement Learning (2016) — 329 citations
- Learning to Learn for Global Optimization of Black Box Functions (2016) — 43 citations
- Hyperbolic Attention Networks (2018) — 276 citations
- Learning to Learn without Gradient Descent by Gradient Descent (2016) — 329 citations
- Learning Awareness Models (2018) — 49 citations
- Task-Relevant Adversarial Imitation Learning (2019) — 65 citations
- From Group to Individual Labels Using Deep Features (2015) — 330 citations
- Making Efficient Use of Demonstrations to Solve Hard Exploration Problems (2019) — 97 citations
- Noisy Activation Functions (2016) — 306 citations
- Extraction of Salient Sentences from Labelled Documents (2014) — 145 citations
- Positive-Unlabeled Reward Learning (2019) — 46 citations
- A Framework for Data-Driven Robotics (2019) — 30 citations