satlins

(To be removed) Symmetric saturating linear transfer function

satlins 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

Syntax

A = satlins(N,FP)


Description

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

A = satlins(N,FP) takes N and an optional argument,

N	S-by-Q matrix of net input (column) vectors
FP	Struct of function parameters (optional, ignored)

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

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

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

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

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

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

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

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

Examples

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

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

Algorithms

satlins(n) = -1, if n <= -1
n, if -1 <= n <= 1
1, if 1 <= n

Version History

Introduced before R2006a

R2026a: satlins will be removed

satlins will be removed in a future release.

To learn more about using activation and transfer functions in neural networks, see these examples and topics:

• Build Networks with Deep Network Designer

• List of Deep Learning Layers

• List of Functions with dlarray Support

• Compare Activation Layers

• Example Deep Learning Network Architectures

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.