feedForwardPass: Forward uncertainty propagation for derivative calculation

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

Description

This function feeds the neural network forward from input data to responses and considers components required for derivative calculations.

Usage

feedForwardPass(NN, theta, states)

Arguments

NN	Lists the structure of the neural network
theta	List of parameters
states	List of states

Value

• Updated states

• Mean vectors of activation units' first derivative

• Covariance matrices of activation units' first derivative

• Mean vectors of activation units' second derivative

• Covariance matrices of activation units' second derivative

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