Andreas Loukas

Artificial Intelligence · 2019–2021

A researcher in the Science corpus: 4 papers; trusts 337 researchers and is trusted by 43 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 73 citations into it; #4,891 of 35,345 by trust here, #7,471 by citations
• Computer Vision and Pattern Recognition — 46 citations into it; #8,564 of 21,575 by trust here, #7,421 by citations
• Model Architectures — 45 citations into it; #846 of 2,278 by trust here, #810 by citations
• Natural Language Processing — 23 citations into it
• Large Language Models — 15 citations into it
• Graph Learning — 13 citations into it
• Efficiency & Compression — 11 citations into it
• Computational Theory and Mathematics — 9 citations into it

Whom Andreas Loukas trusts overall

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

1. Mark Newman
2. Geoffrey E. Hinton
3. Kaiming He
4. Yoshua Bengio
5. Diederik P. Kingma
6. Alex Krizhevsky
7. Thomas Kipf
8. Max Welling
9. Ilya Sutskever
10. Yann LeCun

Who trusts Andreas Loukas overall

1. Petar Velickovic
2. Xiyuan Wang
3. Vikas K. Garg
4. Giorgos Bouritsas
5. Dongsheng Luo
6. Muhan Zhang
7. Vijay Prakash Dwivedi
8. Jean-Baptiste Cordonnier
9. Stefanie Sabrina Jegelka
10. Fabrizio Frasca

Papers from Andreas Loukas's perspective

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

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. ImageNet Large Scale Visual Recognition Challenge
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• On the Relationship between Self-Attention and Convolutional Layers (2019) — 645 citations
• What graph neural networks cannot learn: depth vs width (2019) — 345 citations
• Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth (2021) — 569 citations
• Multi-Head Attention: Collaborate Instead of Concatenate (2020) — 180 citations