Markus Püschel

Artificial Intelligence · 2005–2019

A researcher in the Science corpus: 6 papers; trusts 29 researchers and is trusted by 17 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 50 citations into it; #17,466 of 35,345 by trust here, #21,878 by citations
• Safety, Robustness & Interpretability — 43 citations into it
• Computer Vision and Pattern Recognition — 27 citations into it; #15,063 of 21,575 by trust here, #16,367 by citations
• Computational Theory and Mathematics — 12 citations into it; #7,986 of 12,182 by trust here, #5,046 by citations
• Program Analysis & Verification — 12 citations into it
• Computer Networks and Communications — 10 citations into it; #3,284 of 9,886 by trust here, #3,638 by citations
• Computational Mechanics — 9 citations into it; #3,913 of 10,001 by trust here, #3,652 by citations
• Hardware and Architecture — 8 citations into it; #865 of 1,551 by trust here, #1,384 by citations

Whom Markus Püschel trusts overall

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

1. Alex Krizhevsky
2. Rüdiger Ehlers
3. Gagandeep Singh
4. Nicholas Carlini
5. Matthew Mirman
6. Matteo Frigo
7. Ian J. Goodfellow
8. Radford M. Neal
9. Yann LeCun
10. Antoine Miné

Who trusts Markus Püschel overall

1. Gagandeep Singh
2. Timon Gehr
3. Huan Zhang
4. Hadi Salman
5. Matt Jordan
6. Ashwin K. Vijayakumar
7. Mohammad Rostami
8. Jason Ansel
9. Petar Tsankov
10. Shiqi Wang

Papers from Markus Püschel's perspective

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

1. Gradient-based learning applied to document recognition
2. ImageNet classification with deep convolutional neural networks
3. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
4. Learning Multiple Layers of Features from Tiny Images
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. Intriguing properties of neural networks
7. ImageNet: A large-scale hierarchical image database
8. Long Short-Term Memory
9. Attention is All you Need (Neural Information Processing Systems)
10. Explaining and Harnessing Adversarial Examples

Their papers

• An abstract domain for certifying neural networks (2019) — 847 citations
• D-ADMM: A Communication-Efficient Distributed Algorithm for Separable Optimization (2012) — 399 citations
• SPIRAL: Code Generation for DSP Transforms (2005) — 975 citations
• Fast polyhedra abstract domain (2017) — 116 citations
• Fast and Effective Robustness Certification (2018) — 541 citations
• Multiplierless multiple constant multiplication (2007) — 505 citations