mae

Mean absolute error performance function

Syntax

perf = mae(E,Y,X)

dPerf_dx = mae('dx',E,Y,X,perf)

info = mae('code')

Description

perf= mae(E,Y,X)takes a matrix or cell array of error vectors,E, and optionally a matrix or cell array of output vectors,Y, a vector of all weight and bias values,X, and returns network performance as the mean of absolute errors,perf.

dPerf_dx= mae('dx',E,Y,X,perf)returns the derivative ofperfwith respect toX.

info = mae('code')returns useful information for eachcodecharacter vector:

mae('name')returns the name of this function.
mae('pnames')returns the names of the training parameters.
mae('pdefaults')returns the default function parameters.

Examples

collapse all

Calculate Network Performance with`'mae'`

This example shows how to calculate the network performance as the mean of absolute errors.

Create and configure a perceptron to have one input and one neuron:

net = perceptron; net = configure(net,0,0);

The network is given a batch of inputsP. The error is calculated by subtracting the outputAfrom targetT. Then the mean absolute error is calculated.

p = [-10 -5 0 5 10]; t = [0 0 1 1 1]; y = net(p) e = t-y perf = mae(e)

Note thatmaecan be called with only one argument because the other arguments are ignored.maesupports those arguments to conform to the standard performance function argument list.

Input Arguments

collapse all

`E`—Errors
vector|matrix|cell array

Errors, specified as a vector, a matrix, or a cell array.

`Y`—Outputs
vector|matrix|cell array

Network outputs, specified as a vector, a matrix, or a cell array.

`X`—Weight and bias
vector

Weight and bias values, specified as a vector.

Output Arguments

collapse all

`perf`— Network performance
scalar

Network performance as the mean of absolute errors, returned as a scalar.

`dPerf_dx`——衍生的网络性能rmance
scalar

Derivative ofperfwith respect toX, returned as a scalar.

More About

collapse all

Network Use

You can create a standard network that usesmaewithperceptron.

To prepare a custom network to be trained withmae, setnet.performFcnto'mae'. This automatically setsnet.performParamto the empty matrix[], becausemaehas no performance parameters.

In either case, callingtrainoradapt, results inmaebeing used to calculate performance.

mae

Syntax

Description

Examples

Calculate Network Performance with`'mae'`