fcCovwdowdiwdi: Covariance between next layer product and current layer...

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

Description

This function calculates covariance cov(wdo,wdiwdi) of weights times derivatives products terms when there are one product in next layer and two in current.

Usage

fcCovwdowdiwdi(mpdi, Cdgoddgik, ni, no, B)

Arguments

mpdi	Mean vector of first derivative product wd of current layer
Cdgoddgik	Covariance between weights times derivatives from consecutive layers
ni	Number of units in current layer
no	Number of units in next layer
B	Batch size

Value

Covariance cov(wdo,wdi*wdi) of weights times derivatives products terms when there is one product in next layer and two in current

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