fcDerivative3: Products of first derivatives multiplied to second derivative...

In mgoulet847/tagi: Tractable Approximate Gaussian Inference in Neural Networks

Description

This function calculates mean of product of derivatives, when new product term involves product of two first derivatives (wdwd) from the same layer multiplied to second derivatives (wdd) from next layer.

Usage

fcDerivative3(
  mw,
  Sw,
  mwo,
  mao,
  mai,
  mdao,
  mdai,
  Sdai,
  mpdi,
  mdgo,
  mdgo2,
  Caow,
  Caoai,
  Cdow,
  Cdodi,
  acto,
  acti,
  ni,
  no,
  no2,
  B,
  dlayer
)

Arguments

mw	Mean vector of weights for the current layer
Sw	Covariance of weights for the current layer
mwo	Mean vector of weights for the next layer
mao	Mean vector of activation units from next layer
mai	Mean vector of activation units from current layer
mdao	Mean vector of activation units' first derivative from next layer
mdai	Mean vector of activation units' first derivative from current layer
Sdai	Covariance of activation units' first derivative from current layer
mpdi	Mean vector of first derivative product wd of current layer
mdgo	Mean vector of product of derivatives in next layer
mdgo2	Mean vector of product of derivatives in second next layer
Caow	Covariance between activation units and weights
Caoai	Covariance between activation units from current and next layers
Cdow	Covariance between first derivatives and weights
Cdodi	Covariance between first derivatives from current and next layers
acto	Activation function index for next layer defined by activationFunIndex
acti	Activation function index for current layer defined by activationFunIndex
ni	Number of units in current layer
no	Number of units in next layer
no2	Number of units in second next layer
B	Batch size
dlayer	TRUE if derivatives will be in respect to current layer

Value

Mean of product terms for second derivative calculations

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