fcCovawaa: Covariance between activation units and weights

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

Description

This function calculates covariance between activation units and weights and covariance between activation units from consecutive layers.

Usage

fcCovawaa(mw, Sw, Jo, mai, Sai, ni, no, B)

Arguments

mw	Mean vector of weights for the current layer
Sw	Covariance of weights for the current layer
Jo	Jacobian of next layer
mai	Mean vector of activation units from current layer
Sai	Covariance of activation units from current layer
ni	Number of units in current layer
no	Number of units in next layer
B	Batch size

Value

• Covariance between activation units and weights

• Covariance between activation units from current and next layers

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