Philipp Petersen

About Philipp Petersen

Philipp Petersen, With an exceptional h-index of 18 and a recent h-index of 18 (since 2020), a distinguished researcher at Universität Wien, specializes in the field of Applied Harmonic Analysis, Differential equations, Neural network approximation.

His recent articles reflect a diverse array of research interests and contributions to the field:

Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks

Efficient Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders

Mathematical capabilities of chatgpt

VC dimensions of group convolutional neural networks

Exponential ReLU neural network approximation rates for point and edge singularities

Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems

Large language models for mathematicians

Neural network approximation and estimation of classifiers with classification boundary in a Barron class

Philipp Petersen Information

University

Position

___

Citations(all)

2200

Citations(since 2020)

2084

Cited By

738

hIndex(all)

18

hIndex(since 2020)

18

i10Index(all)

22

i10Index(since 2020)

20

Email

University Profile Page

Google Scholar

Philipp Petersen Skills & Research Interests

Applied Harmonic Analysis

Differential equations

Neural network approximation

Top articles of Philipp Petersen

Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks

arXiv preprint arXiv:2404.14875

2024/4/23

Efficient Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders

arXiv preprint arXiv:2404.04549

2024/4/6

Mathematical capabilities of chatgpt

arXiv preprint arXiv:2301.13867

2023/1/31

VC dimensions of group convolutional neural networks

Neural Networks

2024/1/1

Exponential ReLU neural network approximation rates for point and edge singularities

Foundations of Computational Mathematics

2023/6

Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems

Analysis and Applications

2023/1/19

Large language models for mathematicians

arXiv preprint arXiv:2312.04556

2023/12/7

Neural network approximation and estimation of classifiers with classification boundary in a Barron class

The Annals of Applied Probability

2023/8

Philipp Petersen
Philipp Petersen

H-Index: 11

Felix Voigtlaender
Felix Voigtlaender

H-Index: 9

Limitations of neural network training due to numerical instability of backpropagation

arXiv preprint arXiv:2210.00805

2022/10/3

Deep microlocal reconstruction for limited-angle tomography

Applied and Computational Harmonic Analysis

2022/7/1

Gitta Kutyniok
Gitta Kutyniok

H-Index: 35

Philipp Petersen
Philipp Petersen

H-Index: 11

Mathematics of Machine Learning

2022/4/18

A theoretical analysis of deep neural networks and parametric PDEs

Constructive Approximation

2022/2

Gitta Kutyniok
Gitta Kutyniok

H-Index: 35

Philipp Petersen
Philipp Petersen

H-Index: 11

Optimal learning of high-dimensional classification problems using deep neural networks

arXiv preprint arXiv:2112.12555

2021/12/23

Philipp Petersen
Philipp Petersen

H-Index: 11

Felix Voigtlaender
Felix Voigtlaender

H-Index: 9

Die moderne Mathematik des tiefen Lernens

Mitteilungen der Deutschen Mathematiker-Vereinigung

2021/12/1

Numerical solution of the parametric diffusion equation by deep neural networks

Journal of Scientific Computing

2021/7

Philipp Petersen
Philipp Petersen

H-Index: 11

Gitta Kutyniok
Gitta Kutyniok

H-Index: 35

The modern mathematics of deep learning

arXiv preprint arXiv:2105.04026

2021/5/9

Topological properties of the set of functions generated by neural networks of fixed size

Foundations of computational mathematics

2021/4

Philipp Petersen
Philipp Petersen

H-Index: 11

Felix Voigtlaender
Felix Voigtlaender

H-Index: 9

Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs

Advances in Computational Mathematics

2021/2

Fabian Laakmann
Fabian Laakmann

H-Index: 1

Philipp Petersen
Philipp Petersen

H-Index: 11

Γ-convergence of a shearlet-based Ginzburg–Landau energy

Applied and Computational Harmonic Analysis

2020/11/1

Error bounds for approximations with deep ReLU neural networks in norms

Analysis and Applications

2020/9/19

See List of Professors in Philipp Petersen University(Universität Wien)

Co-Authors

academic-engine