Allan Pinkus

Model Architectures · 1993–2009

A researcher in the Science corpus: 7 papers; trusts 10 researchers and is trusted by 23 researchers here, as inferred from the citation graph.

Subfields

• Model Architectures — 12 citations into it
• Statistical Learning Theory — 7 citations into it

Whom Allan Pinkus trusts overall

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

1. Eric B. Baum
2. Ingo Steinwart
3. Kurt Hornik
4. Yuly Makovoz
5. Tianping Chen
6. Charles A. Micchelli
7. Wolfgang Dahmen
8. Halbert White
9. Vladimir Naumovich Vapnik
10. Vladimir Naumovich Vapni

Who trusts Allan Pinkus overall

1. Francis R. Bach
2. Hrushikesh Narhar Mhaskar
3. Tomaso A. Poggio
4. Alessandro Rudi
5. Johannes Schmidt-Hieber
6. Shaked Brody
7. Lorenzo Rosasco
8. Lu Lu
9. Dmitry Yarotsky
10. Qianli Liao

Papers from Allan Pinkus's perspective

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

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

Their papers

• Strictly Positive Definite Functions on a Real Inner Product Space (2004) — 39 citations
• Totally Positive Matrices (2009) — 178 citations
• Encyclopaedia of Mathematics, Supplement III (2002) — 57 citations
• Weierstrass and Approximation Theory (2000) — 110 citations
• Approximation theory of the MLP model in neural networks (1999)
• Functions that preserve families of positive semidefinite matrices (1995)
• Original Contribution: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function (1993)