Patrick LeGresley

Artificial Intelligence · 2000–2022

A researcher in the Science corpus: 7 papers; trusts 34 researchers and is trusted by 31 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 152 citations into it; #10,815 of 35,345 by trust here, #2,166 by citations
• Natural Language Processing — 78 citations into it
• Computer Vision and Pattern Recognition — 62 citations into it
• Optimization & Training — 44 citations into it; #1,225 of 2,601 by trust here, #325 by citations
• Large Language Models — 40 citations into it
• Model Architectures — 35 citations into it
• Hardware and Architecture — 20 citations into it

Whom Patrick LeGresley trusts overall

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

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Ilya Sutskever
5. Alex Krizhevsky
6. Alec Radford
7. Kaiming He
8. Jimmy Ba
9. Noam Shazeer
10. Quoc V. Le

Who trusts Patrick LeGresley overall

1. Kevin T. Carlberg
2. Marco Fossati
3. Jan S. Hesthaven
4. Charbel Farhat
5. Tino Franz
6. David J. J. Toal
7. Samyam Rajbhandari
8. Anthony T. Patera
9. Tri Dao
10. Charbel Bou-Mosleh

Papers from Patrick LeGresley's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Attention is All you Need (Neural Information Processing Systems)
3. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
8. Gradient-based learning applied to document recognition
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)

Their papers

• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism (2019) — 2,986 citations
• Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model (2022) — 859 citations
• Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM (2021) — 1,287 citations
• Airfoil design optimization using reduced order models based on proper orthogonal decomposition (2000) — 178 citations
• Efficient Large-Scale Language Model Training on GPU Clusters (2021) — 108 citations
• Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin (2015) — 3,177 citations
• Investigation of non-linear projection for POD based reduced order models for Aerodynamics (2001) — 166 citations