fcMeanVarDlayer: Mean and variance of weights times derivatives products terms

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

Description

This function calculates mean and variance of weights times derivatives products terms.

Usage

fcMeanVarDlayer(mx, Sx, my, mye, Sy, Cxy, ni, no, no2, B)

Arguments

mx	Mean vector of inputs
Sx	Variance of inputs
my	Mean vector of outputs
mye	Mean derivatives at each node in next layer
Sy	Variance of outputs
Cxy	Covariance between inputs and outputs
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

Value

• Mean of weights times derivatives products terms

• Covariance between weights times derivatives products terms

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