meanVar: Mean, Jacobian and variance of activated units

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

Description

This function returns mean vector μ_{A}, Jacobian matrix evaluated at μ_{Z} and covariance matrix of activation units Σ_{A}.

Usage

meanVar(z, mz, Sz, funIdx)

Arguments

z	Vector of units for the current layer
mz	Mean vector of units for the current layer μ_{Z}
Sz	Covariance matrix of units for the current layer Σ_{Z}
funIdx	Activation function index defined by activationFunIndex

Value

• Mean vector of activation units for the current layer μ_{A}

• Covariance matrix activation units for the current layer Σ_{A}

• Jacobian matrix evaluated at μ_{Z}

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