fcCovdz: Covariance between derivatives and hidden Units

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

Description

This function calculates covariance between derivatives and hidden units.

Usage

fcCovdz(mao, mai, Caizi, Caozi, acto, acti, ni, no, B)

Arguments

mao	Mean vector of activation units from next layer
mai	Mean vector of activation units from current layer
Caizi	covariance between activation and hidden layers (same layer)
Caozi	covariance between activation (next layer) and hidden (current) 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 derivative (next) and hidden (current) layers

• Covariance between derivative and hidden layers (same layer)

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