Guillaume Desjardins
Artificial Intelligence · 2010–2019
A researcher in the Science corpus: 18 papers; trusts 652 researchers and is trusted by 2,425 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 226 citations into it; #563 of 36,961 by trust here, #243 by citations
- Computer Vision and Pattern Recognition — 104 citations into it; #2,499 of 21,973 by trust here, #2,369 by citations
- Reinforcement Learning — 66 citations into it; #1,712 of 2,250 by trust here, #559 by citations
- Optimization & Training — 64 citations into it; #781 of 2,605 by trust here, #61 by citations
- Probabilistic & Bayesian Methods — 51 citations into it; #671 of 1,526 by trust here, #618 by citations
- Model Architectures — 41 citations into it; #870 of 2,288 by trust here, #232 by citations
- Representation & Self-Supervised Learning — 38 citations into it; #802 of 3,156 by trust here, #136 by citations
- Cognitive Neuroscience — 35 citations into it
Whom Guillaume Desjardins trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Ruslan Salakhutdinov
- Geoffrey E. Hinton
- Yoshua Bengio
- Radford M. Neal
- Tijmen Tieleman
- Yann LeCun
- Alex Krizhevsky
- James Martens
- Diederik P. Kingma
- Marc'Aurelio Ranzato
Who trusts Guillaume Desjardins overall
- Yoshua Bengio
- Kyunghyun Cho
- Ruslan Salakhutdinov
- James Martens
- Asja Fischer
- Ping Luo
- Sergey Levine
- Roger Baker Grosse
- Fei Ye
- Trevor Darrell
Papers from Guillaume Desjardins's perspective
Ordered by how strongly the researchers Guillaume Desjardins 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)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- 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
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Overcoming catastrophic forgetting in neural networks (2016) — 10,384 citations
- Progressive Neural Networks (2016) — 2,948 citations
- Policy Distillation (2015) — 888 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- Natural Neural Networks (2015) — 191 citations
- Disentangling Factors of Variation via Generative Entangling (2012) — 105 citations
- Theano: A CPU and GPU Math Compiler in Python (2010) — 862 citations
- Understanding disentangling in β-VAE (2018) — 962 citations
- Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines (2010) — 122 citations
- Compress and Control (2014) — 30 citations
- Combining modality specific deep neural networks for emotion recognition in video (2013) — 397 citations
- Information asymmetry in KL-regularized RL (2019) — 107 citations
- Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines (2013) — 32 citations
- On Tracking The Partition Function (2011) — 28 citations
- Theano: Deep Learning on GPUs with Python (2012) — 280 citations
- Reply to Huszár: The elastic weight consolidation penalty is empirically valid (2018) — 16 citations
- Unsupervised and Transfer Learning Challenge: a Deep Learning Approach (2011) — 241 citations
- Parallel Tempering for Training of Restricted Boltzmann Machines (2010) — 85 citations