feedBackward: Backpropagation

Description Usage Arguments Value See Also

View source: R/tagi.R

Description

This function feeds the neural network backward from responses to input data.

Usage

1
feedBackward(NN, mp, Sp, mz, Sz, Czw, Czb, Czz, y)

Arguments

NN

Lists the structure of the neural network

mp

Mean vectors of parameters for each layer μ_{θ}

Sp

Covariance matrices of parameters for each layer Σ_{θ}

mz

Mean vectors of units for each layer μ_{Z}

Sz

Covariance matrices of units for each layer Σ_{Z}

Czw

Covariance matrices between units and weights for each layer Σ_{ZW}

Czb

Covariance matrices between units and biases for each layer Σ_{ZB}

Czz

Covariance matrices between previous and current units for each layer Σ_{ZZ^{+}}

y

Response data

Value

See Also

backwardHiddenStateUpdate, backwardParameterUpdate, forwardHiddenStateUpdate


mgoulet847/tagi documentation built on Dec. 21, 2021, 5:10 p.m.