meanVarDev: Mean and variance of activated units for derivatives

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

Description

This function calculates mean vector and covariance matrix of activation units' derivatives.

Usage

meanVarDev(mz, Sz, funIdx, bound)

Arguments

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
bound	If layer is bound

Value

• Mean vector of activation units' first derivative

• Covariance matrix of activation units' first derivative

• Mean vector activation units' second derivative

• Covariance matrix activation units' second derivative

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