satlin

(To be removed) Saturating linear transfer function

satlin will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Graph and Symbol

Saturating linear transfer function. The function returns 0 if input n is less than or equal to 0, n if n is greater than or equal and less than or equal to 1, 1 if n is greater than or equal to 1.

Syntax

A = satlin(N,FP)

Description

satlin is a neural transfer function. Transfer functions calculate a layer’s output from its net input.

A = satlin(N,FP) takes two inputs,

N

S-by-Q matrix of net input (column) vectors

FP

Struct of function parameters (ignored)

and returns A, the S-by-Q matrix of N’s elements clipped to [0, 1].

info = satlin('code') returns useful information for each supported code character vector:

satlin('name') returns the name of this function.

satlin('output',FP) returns the [min max] output range.

satlin('active',FP) returns the [min max] active input range.

satlin('fullderiv') returns 1 or 0, depending on whether dA_dN is S-by-S-by-Q or S-by-Q.

satlin('fpnames') returns the names of the function parameters.

satlin('fpdefaults') returns the default function parameters.

Examples

Here is the code to create a plot of the satlin transfer function.

n = -5:0.1:5;
a = satlin(n);
plot(n,a)

Assign this transfer function to layer i of a network.

net.layers{i}.transferFcn = 'satlin';

Algorithms

a = satlin(n) = 0, if n <= 0
n, if 0 <= n <= 1
1, if 1 <= n

Version History

Introduced before R2006a

collapse all

See Also

| (Statistics and Machine Learning Toolbox) | (Statistics and Machine Learning Toolbox) | | |

Topics