fcMeanDlayer2row: Mean of weights times derivatives products terms squared (wdo...

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

Description

This function calculates mean of weights times derivatives products terms when adding two of those products from current layer to already calculated expectation that ended with one such product of next layer (i.e. wdo x (wdiwdi)). Mean terms are in array format. Once added, rows need to be summed to aggregate expectations by node*node combinations of current layer.

Usage

fcMeanDlayer2row(mpdi, mpdi2, mdgo, Cwdowdiwdi, ni, no, no2, B)

Arguments

mpdi	Mean vector of first derivative product wd of current layer
mpdi2	Mean array of combination of products of first derivatives
mdgo	Mean vector of product of derivatives in next layer
Cwdowdiwdi	Covariance cov(wdo,(wdi*wdi)) of weights times derivatives products terms when there is one product in next layer and two in current
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

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