network-class: Network
In davharris/mistnet: Stochastic Neural Networks

A reference class object for a mistnet network object.

x: a numeric matrix of predictor variables. One row per observation, one column per predictive feature.
y: a matrix of responses to x. One row per observation, one column per response variable.
layers: a list of layer objects
n.layers: an integer corresponding to length(layers)
dataset.size: an integer corresponding to the number of rows in x and y
n.minibacth: an integer specifying the number of rows to include in each stochastic estimate of the likelihood gradient.
n.importance.samples: an integer
importance.weights: a numeric matrix containing the weights associated with the most recent round of importance sampling. (one row per observation, one column per Monte Carlo sample).
loss: the a loss object
sampler: the function used to generate Monte Carlo samples for importance sampling
completed.iterations: a counter that increments after each iteration of model fitting
debug: a logical flag indicating whether special debugging measures should be enabled. Useful for diagnosing problems with the model, but potentially slow.