Brandon Reagen

Artificial Intelligence · 2014–2020

A researcher in the Science corpus: 13 papers; trusts 166 researchers and is trusted by 5 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 186 citations into it; #29,162 of 35,345 by trust here, #10,207 by citations
• Computer Vision and Pattern Recognition — 172 citations into it; #13,057 of 21,575 by trust here, #4,988 by citations
• Electrical and Electronic Engineering — 113 citations into it; #16,457 of 16,539 by trust here, #4,881 by citations
• Efficiency & Compression — 78 citations into it; #1,192 of 1,264 by trust here, #483 by citations
• Model Architectures — 37 citations into it
• Evaluation & Benchmarks — 35 citations into it
• Natural Language Processing — 26 citations into it
• Computational Theory and Mathematics — 20 citations into it

Whom Brandon Reagen trusts overall

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

1. Yann LeCun
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Karen Simonyan
5. Yoshua Bengio
6. Kaiming He
7. Ilya Sutskever
8. Andrew Zisserman
9. Diederik P. Kingma
10. Craig Gentry

Who trusts Brandon Reagen overall

1. Udit Gupta
2. Georgios Georgiadis
3. Lillian Pentecost
4. Weizhe Hua
5. Sang-Min Park
6. Hanhwi Jang
7. Tien-Ju Yang
8. Minsoo Rhu
9. Marton Havasi
10. Renzo Andri

Papers from Brandon Reagen's perspective

Ordered by how strongly the researchers Brandon Reagen 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. Long Short-Term Memory
4. Gradient-based learning applied to document recognition
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. ImageNet: A large-scale hierarchical image database
7. Attention is All you Need (Neural Information Processing Systems)
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Going deeper with convolutions

Their papers

• Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators (2016) — 613 citations
• Fathom: reference workloads for modern deep learning methods (2016) — 189 citations
• DeepRecSys: A System for Optimizing End-To-End At-Scale Neural Recommendation Inference (2020) — 211 citations
• Ares: A framework for quantifying the resilience of deep neural networks (2018) — 352 citations
• MaxNVM: Maximizing DNN Storage Density and Inference Efficiency with Sparse Encoding and Error Mitigation (2019) — 35 citations
• MASR: A Modular Accelerator for Sparse RNNs (2019) — 48 citations
• Cheetah: Optimizing and Accelerating Homomorphic Encryption for Private Inference (2020) — 187 citations
• RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing (2019) — 273 citations
• Machine Learning at Facebook: Understanding Inference at the Edge (2019) — 490 citations
• The Architectural Implications of Facebook's DNN-Based Personalized Recommendation (2019) — 330 citations
• Cognitive Computing Safety: The New Horizon for Reliability / The Design and Evolution of Deep Learning Workloads (2017) — 10 citations
• Weightless: Lossy Weight Encoding For Deep Neural Network Compression (2017) — 42 citations
• MachSuite: Benchmarks for accelerator design and customized architectures (2014) — 342 citations