Figure - available via license: Creative Commons Attribution-ShareAlike 4.0 International
Content may be subject to copyright.
Download
View publication
Time to get accuracy 10 −2 by adaptive methods in oscillators problem parameterized by NN

Time to get accuracy 10 −2 by adaptive methods in oscillators problem parameterized by NN

Source publication
Figure 1. Log-log plot of the global error of trajectories (z(t), v(t))...
Figure 2. Error landscape of ALF and Y4 methods for Kepler problem...
Time to reach accuracy 10 −8 using adaptive methods in the Kepler problem
Time to reach accuracy 10 −4 using adaptive methods in nonlinear...
Time to get accuracy 10 −2 by adaptive methods in oscillators problem...
Adaptive higher order reversible integrators for memory efficient deep learning
Preprint
Full-text available
  • Oct 2024
The depth of networks plays a crucial role in the effectiveness of deep learning. However, the memory requirement for backpropagation scales linearly with the number of layers, which leads to memory bottlenecks during training. Moreover, deep networks are often unable to handle time-series appearing at irregular intervals. These issues can be resol...
Cite
Download full-text

Context in source publication

Context 1
... results presented in Table 3 show the better performance of the higher order method. ...