meanA: Calculate mean of activated units
In mgoulet847/tagi: Tractable Approximate Gaussian Inference in Neural Networks

This function uses lineratization to estimate the activation units mean vector μ_{A} and the Jacobian matrix evaluated at μ_{Z}.

1	meanA(z, mz, funIdx)

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

A list which contains the activation units mean vector μ_{A} and the Jacobian matrix evaluated at μ_{Z}

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

mgoulet847/tagi index

README.md

Note that we can't provide technical support on individual packages. You should contact the package authors for that.

Description