learnos :: Functions (Neural Network Toolbox™)

learnos

Purpose

Outstar weight learning function

Syntax

[dW,LS] = learnos(W,P,Z,N,A,T,E,gW,gA,D,LP,LS)
info = learnos(code)

Description

learnos is the outstar weight learning function.

learnos(W,P,Z,N,A,T,E,gW,gA,D,LP,LS) takes several inputs,

W
S x R weight matrix (or S x 1 bias vector)

P
R x Q input vectors (or ones(1,Q))

Z
S x Q weighted input vectors

N
S x Q net input vectors

A
S x Q output vectors

T
S x Q layer target vectors

E
S x Q layer error vectors

gW
S x R weight gradient with respect to performance

gA
S x Q output gradient with respect to performance

D
S x S neuron distances

LP
Learning parameters, none, LP = []

LS
Learning state, initially should be = []

`W`	`S` x `R` weight matrix (or `S` x `1` bias vector)
`P`	`R` x `Q` input vectors (or ones(`1`,`Q`))
`Z`	`S` x `Q` weighted input vectors
`N`	`S` x `Q` net input vectors
`A`	`S` x `Q` output vectors
`T`	`S` x `Q` layer target vectors
`E`	`S` x `Q` layer error vectors
`gW`	`S` x `R` weight gradient with respect to performance
`gA`	`S` x `Q` output gradient with respect to performance
`D`	`S` x `S` neuron distances
`LP`	Learning parameters, none, `LP = []`
`LS`	Learning state, initially should be = `[]`

and returns

dW
S x R weight (or bias) change matrix

LS
New learning state

`dW`	`S` x `R` weight (or bias) change matrix
`LS`	New learning state

Learning occurs according to learnos's learning parameter, shown here with its default value.

LP.lr - 0.01
Learning rate

`LP.lr - 0.01`	Learning rate

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

'pnames'
Names of learning parameters

'pdefaults'
Default learning parameters

'needg'
Returns 1 if this function uses gW or gA

`'pnames'`	Names of learning parameters
`'pdefaults'`	Default learning parameters
`'needg'`	Returns 1 if this function uses `gW` or `gA`

Examples

Here you define a random input P, output A, and weight matrix W for a layer with a two-element input and three neurons. Also define the learning rate LR.

p = rand(2,1);
a = rand(3,1);
w = rand(3,2);
lp.lr = 0.5;

Because learnos only needs these values to calculate a weight change (see algorithm below), use them to do so.

dW = learnos(w,p,[],[],a,[],[],[],[],[],lp,[])

Network Use

To prepare the weights and the bias of layer i of a custom network to learn with learnos,

Set net.trainFcn to 'trainr'. (net.trainParam automatically becomes trainr's default parameters.)
Set net.adaptFcn to 'trains'. (net.adaptParam automatically becomes trains's default parameters.)
Set each net.inputWeights{i,j}.learnFcn to 'learnos'. Set each net.layerWeights{i,j}.learnFcn to 'learnos'. (Each weight learning parameter property is automatically set to learnos's default parameters.)

To train the network (or enable it to adapt),

Set net.trainParam (or net.adaptParam) properties to desired values.
Call train (adapt).

Algorithm

learnos calculates the weight change dW for a given neuron from the neuron's input P, output A, and learning rate LR according to the outstar learning rule:

```
dw = lr*(a-w)*p'
```

Reference

Grossberg, S., Studies of the Mind and Brain, Drodrecht, Holland, Reidel Press, 1982