Joseph Dean
Artificial Intelligence · 2003–2022
A researcher in the Science corpus: 41 papers; trusts 1,823 researchers and is trusted by 16,536 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,132 citations into it; #48 of 36,961 by trust here, #19 by citations
- Computer Vision and Pattern Recognition — 564 citations into it; #491 of 21,973 by trust here, #78 by citations
- Natural Language Processing — 332 citations into it; #36 of 5,725 by trust here, #27 by citations
- Large Language Models — 233 citations into it; #274 of 810 by trust here, #84 by citations
- Model Architectures — 223 citations into it; #277 of 2,288 by trust here, #131 by citations
- Optimization & Training — 159 citations into it; #929 of 2,605 by trust here, #31 by citations
- Efficiency & Compression — 150 citations into it; #3 of 1,273 by trust here, #3 by citations
- Evaluation & Benchmarks — 131 citations into it
Whom Joseph Dean trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Yann LeCun
- Ilya Sutskever
- Kaiming He
- Diederik P. Kingma
- Quoc V. Le
- Alex Graves
- L. Eon Bottou
Who trusts Joseph Dean overall
- Yoshua Bengio
- Quoc V. Le
- Mohit Bansal
- Zhe Gan
- Dacheng Tao
- Yi Yang
- Ruslan Salakhutdinov
- Trevor Darrell
- Kyunghyun Cho
- Sergey Levine
Papers from Joseph Dean's perspective
Ordered by how strongly the researchers Joseph Dean 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
- Distributed Representations of Words and Phrases and their Compositionality (2013) — 35,459 citations
- Distilling the Knowledge in a Neural Network (2015) — 25,160 citations
- Efficient Estimation of Word Representations in Vector Space (2013) — 34,723 citations
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016) — 7,325 citations
- Large Scale Distributed Deep Networks (2012) — 4,179 citations
- DeViSE: A Deep Visual-Semantic Embedding Model (2013) — 3,053 citations
- TensorFlow: A system for large-scale machine learning (2016) — 19,838 citations
- PaLM: Scaling Language Modeling with Pathways (2022) — 8,214 citations
- Building high-level features using large scale unsupervised learning (2011) — 2,318 citations
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (2017) — 5,113 citations
- Efficient Neural Architecture Search via Parameter Sharing (2018) — 3,045 citations
- Zero-Shot Learning by Convex Combination of Semantic Embeddings (2013) — 981 citations
- Scaling Instruction-Finetuned Language Models (2022) — 4,301 citations
- Carbon Emissions and Large Neural Network Training (2021) — 1,164 citations
- Emergent Abilities of Large Language Models (2022) — 3,700 citations
- Large Language Models in Machine Translation (2007) — 720 citations
- On rectified linear units for speech processing (2013) — 545 citations
- Multilingual acoustic models using distributed deep neural networks (2013) — 330 citations
- Efficiently Scaling Transformer Inference (2022) — 688 citations
- Designing Effective Sparse Expert Models (2022) — 118 citations