Joshua Romoff

Artificial Intelligence · 2017–2020

A researcher in the Science corpus: 5 papers; trusts 92 researchers and is trusted by 4 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 111 citations into it; #25,759 of 35,345 by trust here, #9,870 by citations
• Reinforcement Learning — 96 citations into it
• Computer Vision and Pattern Recognition — 30 citations into it
• Management Science and Operations Research — 28 citations into it
• Probabilistic & Bayesian Methods — 12 citations into it
• Evaluation & Benchmarks — 9 citations into it
• Optimization & Training — 9 citations into it
• Generative Models — 6 citations into it

Whom Joshua Romoff trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Richard S. Sutton
2. Diederik P. Kingma
3. Geoffrey E. Hinton
4. Marc G. Bellemare
5. Volodymyr Mnih
6. Alex Krizhevsky
7. Yoshua Bengio
8. Yann LeCun
9. John Schulman
10. Alex Graves

Who trusts Joshua Romoff overall

1. José Antonio Arjona-Medina
2. Afshin Oroojlooyjadid
3. Tonghan Wang
4. Aimee van Wynsberghe
5. Richard Ryan Williams

Papers from Joshua Romoff's perspective

Ordered by how strongly the researchers Joshua Romoff trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Going deeper with convolutions
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Hybrid Reward Architecture for Reinforcement Learning (2017) — 292 citations
• Randomized Value Functions via Multiplicative Normalizing Flows (2018) — 41 citations
• TarMAC: Targeted Multi-Agent Communication (2018) — 534 citations
• Reward Estimation for Variance Reduction in Deep Reinforcement Learning (2018) — 45 citations
• Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning (2020) — 724 citations