Leila Arras

Artificial Intelligence · 2016–2019

A researcher in the Science corpus: 4 papers; trusts 70 researchers and is trusted by 30 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 95 citations into it; #4,988 of 35,345 by trust here, #6,330 by citations
• Safety, Robustness & Interpretability — 39 citations into it; #926 of 2,251 by trust here, #1,481 by citations
• Computer Vision and Pattern Recognition — 35 citations into it
• Natural Language Processing — 32 citations into it; #1,921 of 5,688 by trust here, #2,172 by citations
• Model Architectures — 18 citations into it
• Biophysics — 17 citations into it
• Reinforcement Learning — 7 citations into it

Whom Leila Arras trusts overall

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

1. Grgoire Montavon
2. Geoffrey E. Hinton
3. J. Urgen Schmidhuber
4. Yoshua Bengio
5. Sepp Hochreiter
6. Karen Simonyan
7. Alex Graves
8. Wojciech Samek
9. Jiwei Li
10. Alex Krizhevsky

Who trusts Leila Arras overall

1. Wojciech Samek
2. Grgoire Montavon
3. Piyawat Lertvittayakumjorn
4. Yonatan Belinkov
5. K. Müller
6. Sebastian Lapuschkin
7. Giulia Vilone
8. Francesca Toni
9. Longo Luca
10. Chiara Zucco

Papers from Leila Arras's perspective

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

Their papers

• "What is relevant in a text document?": An interpretable machine learning approach (2016) — 300 citations
• Explaining Recurrent Neural Network Predictions in Sentiment Analysis (2017) — 385 citations
• Explaining and Interpreting LSTMs (2019) — 89 citations
• Explaining Predictions of Non-Linear Classifiers in NLP (2016) — 123 citations