Amir Yazdanbakhsh

Artificial Intelligence · 2018–2023

A researcher in the Science corpus: 6 papers; trusts 15 researchers and is trusted by 4 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 92 citations into it; #22,948 of 35,345 by trust here, #6,796 by citations
• Computer Vision and Pattern Recognition — 43 citations into it
• Efficiency & Compression — 21 citations into it
• Computer Networks and Communications — 12 citations into it
• Optimization & Training — 9 citations into it
• Signal Processing — 6 citations into it
• Model Architectures — 5 citations into it

Whom Amir Yazdanbakhsh trusts overall

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

1. Song Han
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Yihui He
5. Kaiming He
6. Barret Zoph
7. John Schulman
8. Yann LeCun
9. Yoshua Bengio
10. Yu-hsin Chen

Who trusts Amir Yazdanbakhsh overall

1. Zhiyuan Li
2. Luyu Gao
3. Haiyan Zhao

Papers from Amir Yazdanbakhsh's perspective

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

Their papers

• Self-Refine: Iterative Refinement with Self-Feedback (2023) — 4,061 citations
• Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango (2022) — 153 citations
• SnaPEA: Predictive Early Activation for Reducing Computation in Deep Convolutional Neural Networks (2018) — 168 citations
• ReLeQ : A Reinforcement Learning Approach for Automatic Deep Quantization of Neural Networks (2020) — 61 citations
• Learning Performance-Improving Code Edits (2023) — 155 citations
• ReLeQ: An Automatic Reinforcement Learning Approach for Deep Quantization of Neural Networks (2018)