Afroz Mohiuddin

Artificial Intelligence · 2019–2022

A researcher in the Science corpus: 4 papers; trusts 15 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 116 citations into it; #34,113 of 35,345 by trust here, #3,624 by citations
• Computer Vision and Pattern Recognition — 67 citations into it; #20,793 of 21,575 by trust here, #3,955 by citations
• Model Architectures — 47 citations into it; #2,153 of 2,278 by trust here, #428 by citations

Whom Afroz Mohiuddin trusts overall

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

1. Geoffrey E. Hinton
2. Diederik P. Kingma
3. Noam Shazeer
4. Yoshua Bengio
5. Ilya Sutskever
6. Alex Krizhevsky
7. Yann LeCun
8. Kaiming He
9. Sepp Hochreiter
10. Alex Graves

Who trusts Afroz Mohiuddin overall

1. Tri Dao

Papers from Afroz Mohiuddin's perspective

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

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

Their papers

• Rethinking Attention with Performers (2020) — 2,365 citations
• Model-Based Reinforcement Learning for Atari (2019) — 995 citations
• Sparse is Enough in Scaling Transformers (2021) — 125 citations
• Scaling Up Models and Data with t5x and seqio (2022) — 224 citations