Razvan Pascanu
Artificial Intelligence · 2010–2023
A researcher in the Science corpus: 81 papers; trusts 3,292 researchers and is trusted by 13,575 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 2,210 citations into it; #69 of 36,961 by trust here, #49 by citations
- Computer Vision and Pattern Recognition — 1,043 citations into it; #560 of 21,973 by trust here, #290 by citations
- Reinforcement Learning — 547 citations into it; #388 of 2,250 by trust here, #87 by citations
- Optimization & Training — 438 citations into it; #95 of 2,605 by trust here, #19 by citations
- Model Architectures — 421 citations into it; #70 of 2,288 by trust here, #60 by citations
- Representation & Self-Supervised Learning — 363 citations into it; #300 of 3,156 by trust here, #84 by citations
- Meta & Continual Learning — 242 citations into it; #52 of 1,043 by trust here, #11 by citations
- Cognitive Neuroscience — 213 citations into it; #2,985 of 11,026 by trust here, #1,856 by citations
Whom Razvan Pascanu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Ilya Sutskever
- Diederik P. Kingma
- Alex Krizhevsky
- Alex Graves
- James Martens
- Yann LeCun
- Kaiming He
- J. Urgen Schmidhuber
Who trusts Razvan Pascanu overall
- Yoshua Bengio
- Kyunghyun Cho
- Sergey Levine
- Ruslan Salakhutdinov
- Dacheng Tao
- Quoc V. Le
- Zhe Gan
- Mohit Bansal
- Trevor Darrell
- Li Deng
Papers from Razvan Pascanu's perspective
Ordered by how strongly the researchers Razvan Pascanu 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)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- On the difficulty of training recurrent neural networks (2012) — 6,009 citations
- Overcoming catastrophic forgetting in neural networks (2016) — 10,384 citations
- Progressive Neural Networks (2016) — 2,948 citations
- A simple neural network module for relational reasoning (2017) — 1,703 citations
- Learning to Navigate in Complex Environments (2016) — 958 citations
- Interaction Networks for Learning about Objects, Relations and Physics (2016) — 1,568 citations
- Relational inductive biases, deep learning, and graph networks (2018) — 3,656 citations
- Policy Distillation (2015) — 888 citations
- Imagination-Augmented Agents for Deep Reinforcement Learning (2017) — 599 citations
- Identifying and attacking the saddle point problem in high-dimensional non-convex optimization (2014) — 1,536 citations
- How to Construct Deep Recurrent Neural Networks (2013) — 1,083 citations
- Distral: Robust multitask reinforcement learning (2017) — 628 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- Sim-to-Real Robot Learning from Pixels with Progressive Nets (2016) — 568 citations
- Meta-Learning with Latent Embedding Optimization (2018) — 1,522 citations
- Revisiting Natural Gradient for Deep Networks (2013) — 448 citations
- Understanding the exploding gradient problem (2012) — 563 citations
- Progress & Compress: A scalable framework for continual learning (2018) — 1,048 citations
- Advances in optimizing recurrent networks (2012) — 538 citations
- Pylearn2: a machine learning research library (2013) — 305 citations