Dinfio Documentation — Function Reference: neural_network::back_propagation()

Module neural → Class neural_network → back_propagation()

Description

Do a backward propagation process

neural_network::back_propagation(expected)

Parameters

expected (matrix) — The expected matrix. The matrix must be a row matrix (vector)

Return Value

boolean — Always returns true

Usage Example

import neural
 
model = neural_network([784, 20, 10, 10], 0.01)
 
expected = dataset.outputs(0)
 
model.feed_forward(dataset.inputs(0))
model.back_propagation(expected)
 
error = calculate_error(model.outputs(), expected)