Ari S. Morcos
Artificial Intelligence · 2018–2023
A researcher in the Science corpus: 18 papers; trusts 1,649 researchers and is trusted by 243 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 663 citations into it; #4,146 of 36,961 by trust here, #3,136 by citations
- Computer Vision and Pattern Recognition — 524 citations into it; #3,291 of 21,973 by trust here, #2,104 by citations
- Representation & Self-Supervised Learning — 177 citations into it; #875 of 3,156 by trust here, #1,052 by citations
- Optimization & Training — 120 citations into it
- Model Architectures — 111 citations into it; #2,012 of 2,288 by trust here, #1,834 by citations
- Efficiency & Compression — 76 citations into it
- Scaling & Learning Theory — 67 citations into it
- Natural Language Processing — 61 citations into it
Whom Ari S. Morcos trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Karen Simonyan
- Yann LeCun
- Ilya Sutskever
- Ross B. Girshick
- Christian Szegedy
Who trusts Ari S. Morcos overall
- Maithra Raghu
- Congzheng Song
- Simon Kornblith
- Sara Hooker
- Jonathan Frankle
- Sidak Pal Singh
- Vitaly Shmatikov
- Mitchell A. Gordon
- Jie Hu
- Saurabh Satish Desai
Papers from Ari S. Morcos's perspective
Ordered by how strongly the researchers Ari S. Morcos 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Neural scene representation and rendering (2018) — 674 citations
- Human-level performance in 3D multiplayer games with population-based reinforcement learning (2018) — 819 citations
- ConViT: improving vision transformers with soft convolutional inductive biases (2021) — 1,066 citations
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022) — 1,632 citations
- On the importance of single directions for generalization (2018) — 362 citations
- DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames (2019) — 650 citations
- Insights on representational similarity in neural networks with canonical correlation (2018) — 564 citations
- Measuring abstract reasoning in neural networks (2018) — 408 citations
- Beyond neural scaling laws: beating power law scaling via data pruning (2022) — 656 citations
- Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs (2020) — 164 citations
- Learning to Make Analogies by Contrasting Abstract Relational Structure (2019) — 117 citations
- SemDeDup: Data-efficient learning at web-scale through semantic deduplication (2023) — 307 citations
- The Early Phase of Neural Network Training (2020) — 202 citations
- One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers (2019) — 256 citations
- Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP (2019) — 157 citations
- Stable and low-precision training for large-scale vision-language models (2023) — 94 citations
- Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs (2018) — 44 citations
- A Cookbook of Self-Supervised Learning (2023) — 398 citations