hiddenStateBackwardPass: Backpropagation (states' deltas)

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

Description

This function calculates states' deltas.

Usage

hiddenStateBackwardPass(NN, theta, states, y, Sy, udIdx)

Arguments

NN	Lists the structure of the neural network
theta	List of parameters
states	List of states
y	Response data
Sy	Variance of responses
udIdx	Specific update IDs

Value

• Delta of mean vector of units given y μ_{Z}|y at all layers

• Delta of covariance matrix of units given y Σ_{Z}|y at all layers

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