Jonathan Frankle
Artificial Intelligence · 2018–2020
A researcher in the Science corpus: 12 papers; trusts 1,358 researchers and is trusted by 728 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 314 citations into it; #1,738 of 36,961 by trust here, #2,430 by citations
- Computer Vision and Pattern Recognition — 268 citations into it; #2,155 of 21,973 by trust here, #1,682 by citations
- Efficiency & Compression — 177 citations into it; #22 of 1,273 by trust here, #99 by citations
- Optimization & Training — 74 citations into it; #1,781 of 2,605 by trust here, #1,107 by citations
- Model Architectures — 45 citations into it
- Scaling & Learning Theory — 24 citations into it; #11 of 429 by trust here, #60 by citations
- Electrical and Electronic Engineering — 12 citations into it
- Evaluation & Benchmarks — 11 citations into it
Whom Jonathan Frankle trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Yann LeCun
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Karen Simonyan
- Song Han
- X. Zhang
- Ilya Sutskever
Who trusts Jonathan Frankle overall
- Tianlong Chen
- Michael Crawshaw
- Tri Dao
- Jiahui Yu
- Mitchell Wortsman
- Mingjie Sun
- Utku Evci
- Eugene Lee
- Yi-Lin Sung
- Chaoqi Wang
Papers from Jonathan Frankle's perspective
Ordered by how strongly the researchers Jonathan Frankle trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (2018) — 4,345 citations
- Linear Mode Connectivity and the Lottery Ticket Hypothesis (2019) — 798 citations
- The Lottery Ticket Hypothesis: Training Pruned Neural Networks (2018) — 289 citations
- Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs (2020) — 164 citations
- What is the State of Neural Network Pruning? (2020) — 1,270 citations
- Stabilizing the Lottery Ticket Hypothesis (2019) — 256 citations
- The Lottery Ticket Hypothesis for Pre-trained BERT Networks (2020) — 422 citations
- The Early Phase of Neural Network Training (2020) — 202 citations
- The Lottery Ticket Hypothesis at Scale (2019) — 105 citations
- Comparing Rewinding and Fine-tuning in Neural Network Pruning (2020) — 445 citations
- On the Predictability of Pruning Across Scales (2020) — 48 citations
- Comparing Rewinding and Fine-tuning in Neural Network Pruning (2019) — 21 citations