logsig (Neural Network Toolbox)

Log sigmoid transfer function

A = logsig(N)

info = logsig(code)

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

logsig(N) takes one input,

N - S x Q matrix of net input (column) vectors.

and returns each element of N squashed between 0 and 1.

logsig(code) returns useful information for each code string:

'deriv' - Name of derivative function.

'name' - Full name.

'output' - Output range.

'active' - Active input range.

Examples

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

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

You can create a standard network that uses logsig by calling newff or newcf.

To change a network so a layer uses logsig set net.layers{i}.transferFcn to 'logsig'.

In either case, call sim to simulate the network with purelin.

See newff or newcf for simulation examples.

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