newc (Neural Network Toolbox™)

Neural Network Toolbox™

newc

Provide feedback about this page

Create competitive layer

Syntax

```
net = newc(PR,S,KLR,CLR)
```

Description

Competitive layers are used to solve classification problems.

net = newc(PR,S,KLR,CLR) takes these inputs,

PR
R x 2 matrix of min and max values for R input elements

S
Number of neurons

KLR
Kohonen learning rate (default = 0.01)

CLR
Conscience learning rate (default = 0.001)

`PR`	`R` x `2` matrix of min and max values for `R` input elements
`S`	Number of neurons
`KLR`	Kohonen learning rate (default = 0.01)
`CLR`	Conscience learning rate (default = 0.001)

and returns a new competitive layer.

Properties

Competitive layers consist of a single layer, with the negdist weight function, netsum net input function, and the compet transfer function.

The layer has a weight from the input, and a bias.

Weights and biases are initialized with midpoint and initcon.

Adaption and training are done with trains and trainr, which both update weight and bias values with the learnk and learncon learning functions.

Examples

Here is a set of four two-element vectors P.

```
P = [.1 .8  .1 .9; .2 .9 .1 .8];
```

A competitive layer can be used to divide these inputs into two classes. First a two-neuron layer is created with two input elements ranging from 0 to 1, then it is trained.

net = newc([0 1; 0 1],2);
net = train(net,P);

The resulting network can then be simulated and its output vectors converted to class indices.

```
Y = sim(net,P)
Yc = vec2ind(Y)
```

See Also

sim, init, adapt, train, trains, trainr, newcf

Provide feedback about this page

network newcf

© 1984-2008- The MathWorks, Inc. - Site Help - Patents - Trademarks - Privacy Policy - Preventing Piracy - RSS