Mehdi Mirza
Artificial Intelligence · 2012–2021
A researcher in the Science corpus: 19 papers; trusts 927 researchers and is trusted by 8,580 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 451 citations into it; #515 of 36,961 by trust here, #330 by citations
- Computer Vision and Pattern Recognition — 346 citations into it; #387 of 21,973 by trust here, #204 by citations
- Generative Models — 145 citations into it; #38 of 1,963 by trust here, #28 by citations
- Reinforcement Learning — 134 citations into it; #196 of 2,250 by trust here, #85 by citations
- Optimization & Training — 98 citations into it; #659 of 2,605 by trust here, #222 by citations
- Model Architectures — 76 citations into it; #149 of 2,288 by trust here, #88 by citations
- Representation & Self-Supervised Learning — 65 citations into it
- Probabilistic & Bayesian Methods — 54 citations into it; #771 of 1,526 by trust here, #700 by citations
Whom Mehdi Mirza trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Yann LeCun
- Diederik P. Kingma
- Ruslan Salakhutdinov
- Ilya Sutskever
- Richard S. Sutton
- Radford M. Neal
- Kaiming He
Who trusts Mehdi Mirza overall
- Yoshua Bengio
- Chunyuan Li
- Sergey Levine
- Dacheng Tao
- Kyunghyun Cho
- Zhe Gan
- Trevor Darrell
- Luc Van Gool
- Abhinav Kumar Gupta
- Ruslan Salakhutdinov
Papers from Mehdi Mirza's perspective
Ordered by how strongly the researchers Mehdi Mirza 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
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Asynchronous Methods for Deep Reinforcement Learning (2016) — 10,169 citations
- Conditional Generative Adversarial Nets (2014) — 11,730 citations
- Generative Adversarial Networks (2021) — 30,470 citations
- Generative Adversarial Nets (2014) — 2,369 citations
- An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks (2013) — 1,666 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- Pylearn2: a machine learning research library (2013) — 305 citations
- Unsupervised Predictive Memory in a Goal-Directed Agent (2018) — 206 citations
- Multi-Prediction Deep Boltzmann Machines (2013) — 139 citations
- Optimizing agent behavior over long time scales by transporting value (2018) — 139 citations
- Challenges in representation learning: A report on three machine learning contests (2013) — 2,020 citations
- Disentangling Factors of Variation for Facial Expression Recognition (2012) — 211 citations
- Combining modality specific deep neural networks for emotion recognition in video (2013) — 397 citations
- An investigation of model-free planning (2019) — 130 citations
- Generative adversarial networks (2014) — 4,455 citations
- EmoNets: Multimodal deep learning approaches for emotion recognition in video (2015) — 412 citations
- Physically Embedded Planning Problems: New Challenges for Reinforcement Learning (2020) — 14 citations
- Probing Physics Knowledge Using Tools from Developmental Psychology (2018) — 38 citations
- Maxout Networks (2013) — 2,259 citations