covarianceCzp: Covariance matrices between units and parameters

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

Description

This function calculate the covariance matrices between units and parameters Σ_{ZW} and Σ_{ZB} for a given layer.

Usage

covarianceCzp(ma, Sp, idxFCwwa, idxFCb)

Arguments

ma	Mean vector of activation units from previous layer μ_{A}
Sp	Covariance matrix of parameters for the current layer Σ_{θ}
idxFCwwa	Indices for weights and for activation units for the current and previous layers respectively
idxFCb	Indices for biases of the current layer

Value

• Covariance matrix between units and biases for the current layer Σ_{ZB}

• Covariance matrix between units and weights for the current layer Σ_{ZW}

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