fcCovaz: Covariance between activation and hidden units

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

Description

This function calculates covariance between activation and hidden units.

Usage

fcCovaz(Jo, J, Sz, mw, ni, no, B)

Arguments

Jo	Jacobian of next layer
J	Jacobian of current layer
Sz	Covariance of units from current layer
mw	Mean vector of weights for the current layer
ni	Number of units in current layer
no	Number of units in next layer
B	Batch size

Value

• Covariance between activation and hidden layers (same layer)

• Covariance between activation (next) and hidden (current) layers

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