Skip to main content
. Author manuscript; available in PMC: 2024 Sep 1.
Published in final edited form as: J Comput Phys. 2023 May 9;488:112152. doi: 10.1016/j.jcp.2023.112152

Figure 12:

Figure 12:

Dependence of performance as key hyperparameters are varied. (left) RMS error of the committor as a function of lag time. (right) Relative error in the product used to solve for the lead time as a function of the network depth and lag time. Shading shows the standard deviation from networks trained on ten indpendent data sets resulting from the adaptive sampling scheme used to train the committor; on the right, shading is only shown for the deepest network for clarity.