fcCovDlayer: Covariance between products of derivatives and weights

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

Description

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

Usage

fcCovDlayer(mdgo2, mwo, Cdowdi, ni, no, no2, B)

Arguments

mdgo2	Mean vector of product of derivatives in second next layer
mwo	Mean vector of weights for the next layer
Cdowdi	Covariance between derivatives and weights times derivatives
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

Covariance between weights times derivatives from consecutive layers

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