Main Content

# elliot2sig

Elliot 2 symmetric sigmoid transfer function

## Syntax

```A = elliot2sig(N) ```

## Description

Transfer functions convert a neural network layer’s net input into its net output. This function is a variation on the original Elliot sigmoid function. It has a steeper slope, closer to `tansig`, but is not as smooth at the center.

`A = elliot2sig(N)` takes an `S`-by-`Q` matrix of `S` `N`-element net input column vectors and returns an `S`-by-`Q` matrix `A` of output vectors, where each element of `N` is squashed from the interval ```[-inf inf]``` to the interval `[-1 1]` with an “S-shaped” function.

The advantage of this transfer function over other sigmoids is that it is fast to calculate on simple computing hardware as it does not require any exponential or trigonometric functions. Its disadvantage is that it departs from the classic sigmoid shape around zero.

## Examples

Calculate a layer output from a single net input vector:

```n = [0; 1; -0.5; 0.5]; a = elliot2sig(n);```

Plot the transfer function:

```n = -5:0.01:5; plot(n, elliot2sig(n)) set(gca,'dataaspectratio',[1 1 1],'xgrid','on','ygrid','on') ```

For a network you have already defined, change the transfer function for layer `i`:

` net.layers{i}.transferFcn = 'elliot2sig';`

## See Also

Introduced in R2012b

Download ebook