Pratik Chaudhari
Artificial Intelligence · 2015–2021
A researcher in the Science corpus: 14 papers; trusts 2,008 researchers and is trusted by 142 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 542 citations into it; #2,871 of 36,961 by trust here, #3,544 by citations
- Computer Vision and Pattern Recognition — 245 citations into it; #6,395 of 21,973 by trust here, #3,394 by citations
- Optimization & Training — 185 citations into it; #548 of 2,605 by trust here, #432 by citations
- Reinforcement Learning — 141 citations into it; #1,650 of 2,250 by trust here, #2,004 by citations
- Representation & Self-Supervised Learning — 70 citations into it; #2,288 of 3,156 by trust here, #1,813 by citations
- Management Science and Operations Research — 69 citations into it
- Statistics and Probability — 66 citations into it; #1,967 of 13,188 by trust here, #2,468 by citations
- Model Architectures — 63 citations into it
Whom Pratik Chaudhari trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yoshua Bengio
- Kaiming He
- Yann LeCun
- Ilya Sutskever
- Alex Graves
- L. Eon Bottou
- Max Welling
Who trusts Pratik Chaudhari overall
- Alessandro Achille
- Stefano Soatto
- Charles H. Martin
- Zhanxing Zhu
- Mitch Hill
- Jianyu Wang
- Bin Shi
- Rasool Fakoor
- Samuel L. Smith
- Lukas Balles
Papers from Pratik Chaudhari's perspective
Ordered by how strongly the researchers Pratik Chaudhari 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
- Entropy-SGD: biasing gradient descent into wide valleys (2016) — 882 citations
- A Baseline for Few-Shot Image Classification (2019) — 646 citations
- Stochastic Gradient Descent Performs Variational Inference, Converges to Limit Cycles for Deep Networks (2017) — 339 citations
- P3O: Policy-on Policy-off Policy Optimization (2019) — 66 citations
- Meta-Q-Learning (2019) — 167 citations
- Rethinking the Hyperparameters for Fine-tuning (2020) — 148 citations
- Deep relaxation: partial differential equations for optimizing deep neural networks (2017) — 164 citations
- Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation (2020) — 63 citations
- On the energy landscape of deep networks (2015) — 26 citations
- DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning (2020) — 6 citations
- Continuous Doubly Constrained Batch Reinforcement Learning (2021) — 36 citations
- Model Zoo: A Growing Brain That Learns Continually (2021) — 82 citations
- Parle: parallelizing stochastic gradient descent (2017) — 23 citations
- The Effect of Gradient Noise on the Energy Landscape of Deep Networks (2015) — 16 citations