A theoretical analysis of deep neural networks and parametric PDEs G Kutyniok, P Petersen, M Raslan, R Schneider Constructive Approximation 55 (1), 73-125, 2022 | 177 | 2022 |

Topological properties of the set of functions generated by neural networks of fixed size P Petersen, M Raslan, F Voigtlaender Foundations of Computational Mathematics, 1-70, 2020 | 95 | 2020 |

Numerical solution of the parametric diffusion equation by deep neural networks M Geist, P Petersen, M Raslan, R Schneider, G Kutyniok Journal of Scientific Computing 88 (1), 22, 2021 | 73 | 2021 |

Approximation rates for neural networks with encodable weights in smoothness spaces I Gühring, M Raslan Neural Networks, 2020 | 68 | 2020 |

Expressivity of deep neural networks I Gühring, M Raslan, G Kutyniok arXiv preprint arXiv:2007.04759 34, 2020 | 60 | 2020 |

Anisotropic multiscale systems on bounded domains P Grohs, G Kutyniok, J Ma, P Petersen, M Raslan arXiv preprint arXiv:1510.04538, 2015 | 7* | 2015 |

Unfavorable structural properties of the set of neural networks with fixed architecture P Petersen, M Raslan, F Voigtlaender Proceedings of International Conference on Sampling Theory and Applications …, 2019 | 4 | 2019 |

Deep Learning based Forecasting: a case study from the online fashion industry M Kunz, S Birr, M Raslan, L Ma, Z Li, A Gouttes, M Koren, T Naghibi, ... arXiv preprint arXiv:2305.14406, 2023 | 3 | 2023 |

Solving parametric PDEs with neural networks: unfavorable structure vs. expressive power M Raslan TU Berlin, Institut für Mathematik, 2021 | 2 | 2021 |

Approximation properties of hybrid shearlet-wavelet frames for Sobolev spaces P Petersen, M Raslan Advances in Computational Mathematics 45, 1581-1606, 2019 | 2* | 2019 |

The structure of spaces of neural network functions P Petersen, M Raslan, F Voigtlaender Wavelets and Sparsity XVIII 11138, 144-151, 2019 | 1 | 2019 |

MD 21218, USA K Kawaguchi, G Kutyniok, Y Levine, Q Li, T Merkh, G Montavon, ... | | |