Követés
Shokhrukh Ibragimov
Shokhrukh Ibragimov
University of Münster
E-mail megerősítve itt: uni-muenster.de
Cím
Hivatkozott rá
Hivatkozott rá
Év
Convergence to good non-optimal critical points in the training of neural networks: Gradient descent optimization with one random initialization overcomes all bad non-global …
S Ibragimov, A Jentzen, A Riekert
arXiv preprint arXiv:2212.13111, 2022
142022
Lower bounds for artificial neural network approximations: A proof that shallow neural networks fail to overcome the curse of dimensionality
P Grohs, S Ibragimov, A Jentzen, S Koppensteiner
Journal of Complexity 77, 101746, 2023
112023
On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation
S Ibragimov, A Jentzen, T Kröger, A Riekert
arXiv preprint arXiv:2202.11481, 2022
62022
On the logical skills of large language models: evaluations using arbitrarily complex first-order logic problems
S Ibragimov, A Jentzen, B Kuckuck
arXiv preprint arXiv:2502.14180, 2025
2025
On a functional-differential equation with quasi-arithmetic mean value
S Ibragimov
arXiv preprint arXiv:2005.08369, 2020
2020
A rendszer jelenleg nem tudja elvégezni a műveletet. Próbálkozzon újra később.
Cikkek 1–5