backprop.mistnet_network: Backprop: calculate network gradients using backpropagation

In davharris/mistnet2: Neural Networks with Latent Random Variables

Description

Backprop: calculate network gradients using backpropagation

Usage

## S3 method for class 'mistnet_network'
backprop(network, state, par, ...)

Arguments

network	a network object, as created by mistnet
state	if a network_sate object is provided, it can be used instead of producing a new one with feedforward. This may save some computation time.
par	A list or vector containing the parameters. If not included, network$par_list will be used
...	(currently not used)

Value

a vector of gradients.

davharris/mistnet2 documentation built on May 14, 2019, 9:28 p.m.