logsig

(To be removed) Log-sigmoid transfer function

logsig 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.

Syntax

A = logsig(N)

dA_dN = logsig('dn',N,A,FP)

info = logsig(code)

Description

Tip

To use a logistic sigmoid activation for deep learning, use sigmoidLayer or the dlarray method sigmoid.

A = logsig(N) takes a matrix of net input vectors, N and returns the S-by-Q matrix, A, of the elements of N squashed into [0, 1].

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

dA_dN = logsig('dn',N,A,FP) returns the S-by-Q derivative of A with respect to N. If A or FP are not supplied or are set to [], FP reverts to the default parameters, and A is calculated from N.

info = logsig(code) returns information about this function. For more information, see the code argument description.

Examples

Create a Plot of the logsig Transfer Function

This example shows how to calculate and plot the log-sigmoid transfer function of an input matrix.

Create the input matrix, n. Then call the logsig function and plot the results.

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

Assign this transfer function to layer i of a network.

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

Input Arguments

N — Input matrix

matrix

Net input column vectors, specified as an S-by-Q matrix.

code — Information option

'name' | 'output' | 'active' | 'fullderiv' | 'fpnames' | 'fpdefaults'

Information you want to retrieve from the function, specified as one of the following:

• 'name' returns the name of this function.

• 'output' returns the [min max] output range.

• 'active' returns the [min max] active input range.

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

• 'fpnames' returns the names of the function parameters.

• 'fpdefaults' returns the default function parameters.

Output Arguments

A — Output matrix

matrix

Output vectors, returned as an S-by-Q matrix, where each element of N is squashed from the interval [-inf inf] to the interval [0 1] with an "S-shaped" function.

Algorithms

logsig(n) = 1 / (1 + exp(-n))

Version History

Introduced before R2006a

R2026a: logsig will be removed

logsig 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

To include a sigmoid layer in a layer array or dlnetwork object, use sigmoidLayer. To apply the sigmoid activation to dlarray objects, use the sigmoid function.

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