1 code implementation • 31 Oct 2023 • Veronica Saz Ulibarrena, Philipp Horn, Simon Portegies Zwart, Elena Sellentin, Barry Koren, Maxwell X. Cai
To increase the robustness of a method that uses neural networks, we propose a hybrid integrator that evaluates the prediction of the network and replaces it with the numerical solution if considered inaccurate.
1 code implementation • 26 Oct 2022 • Hugo Melchers, Daan Crommelin, Barry Koren, Vlado Menkovski, Benjamin Sanderse
Of the two trajectory fitting procedures, the discretise-then-optimise approach produces more accurate models than the optimise-then-discretise approach.
no code implementations • 24 Feb 2022 • Lu Xia, Stefano Massei, Michiel E. Hochstenbach, Barry Koren
When implementing the gradient descent method in low precision, the employment of stochastic rounding schemes helps to prevent stagnation of convergence caused by the vanishing gradient effect.
no code implementations • 24 Mar 2021 • Lu Xia, Martijn Anthonissen, Michiel Hochstenbach, Barry Koren
Conventional stochastic rounding (CSR) is widely employed in the training of neural networks (NNs), showing promising training results even in low-precision computations.
no code implementations • 31 May 2020 • Lu Xia, Martijn Anthonissen, Michiel Hochstenbach, Barry Koren
When a sequence of computations is implemented, round-off errors may be magnified or accumulated.