fcCovdwddd: Covariance between derivatives and weights

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

Description

This function calculates covariance between derivatives and weights and covariance between derivatives from consecutive layers.

Usage

fcCovdwddd(mao, Sao, mai, Sai, Caow, Caoai, acto, acti, ni, no, B)

Arguments

mao	Mean vector of activation units from next layer
Sao	Covariance of activation units from next layer
mai	Mean vector of activation units from current layer
Sai	Covariance of activation units from current layer
Caow	Covariance between activation units and weights
Caoai	Covariance between activation units 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
B	Batch size

Value

• Covariance between derivatives and weights

• Covariance between derivatives from current and next layers

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