backprop: Backpropagation

Description Usage Arguments Value

View source: R/nn.R

Description

Runs a backwards pass through the network.

Usage

1
backprop(model, error, forward_pass)

Arguments

model

list of all the weights and biases

error

gradients to the output of the network

forward_pass

intermediate values from the forward pass

Value

list of derivatives after the backwards pass


simpleMLP documentation built on March 28, 2021, 9:07 a.m.