Export 3 results:
Search results for biblio_year:2021
Filters: Author is Michael Rauchensteiner  [Reset Search]
2021
C. Fiedler, M. Fornasier, T. Klock and M. Rauchensteiner. "Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples." arXiv (2021).
2019
M. Fornasier, T. Klock and M. Rauchensteiner. Identifying weights of overcomplete shallow- and two layer neural networksusing few network evaluations. Deepmath Conference, New York, USA, 2019.
M. Fornasier, T. Klock and M. Rauchensteiner. "Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks." Constructive Approximation (2019).