der_vs_state_nlmixr: Generate Derivative versus State (nlmixr2)

Description

This functions allows to generate derivative versus state data for a neural network from a NODE in nlmixr2.

Usage

der_vs_state_nlmixr(
  nn_name,
  min_state = NULL,
  max_state = NULL,
  inputs = NULL,
  est_parms = NULL,
  fit_obj = NULL,
  length_out = 100,
  time_nn = FALSE,
  act = "ReLU",
  beta = 20
)

Value

Dataframe with columns for the state and the corresponding derivatives

Arguments

nn_name: (string) Name of the NN, e.g., “c” for NNc(...)
min_state: (numeric) Value of minimal state for which the derivative should be calculated (optional if inputs is given, ignored if inputs is defined)
max_state: (numeric) Value of maximal state for which the derivative should be calculated (optional if inputs is given, ignored if inputs is defined)
inputs: (numeric vector) Vector of input values for which derivatives should be calculated (optional if min_state and max_state is given)
est_parms: (named vector; semi-optional) Named vector of estimated parameters form fit$fixef. For optionality, see Details.
fit_obj: (nlmixr fit object; semi-optional) The fit-object from nlmixr2(...). For optionality, see Details.
length_out: (numeric) Number of states between min_state and max_state for derivative calculations.
time_nn: (boolean) Whether the neural network to analyze is a time-dependent neural network or not. Default values is FALSE.
act: (string) Activation function used in the NN. Currently "ReLU" and "Softplus" available.
beta: (numeric) Beta value for the Softplus activation function, only applicable if act="Softplus"; Default to 20.

Author

Dominic Bräm

Details

Either est_parms or fit_obj must be given. If both arguments are given, est_parms is prioritized.