learnlv1 :: Functions (Neural Network Toolbox™)

learnlv1

Purpose

LVQ1 weight learning function

Syntax

[dW,LS] = learnlv1(W,P,Z,N,A,T,E,gW,gA,D,LP,LS)
info = learnlv1(code)

Description

learnlv1 is the LVQ1 weight learning function.

learnlv1(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 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` 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 learnlv1's learning parameter, shown here with its default value.

LP.lr - 0.01
Learning rate

`LP.lr - 0.01`	Learning rate

learnlv1(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, weight matrix W, and output gradient gA for a layer with a two-element input and three neurons. Also define the learning rate LR.

p = rand(2,1);
w = rand(3,2);
a = compet(negdist(w,p));
gA = [-1;1; 1];
lp.lr = 0.5;

Because learnlv1 only needs these values to calculate a weight change (see algorithm below), use them to do so.

dW = learnlv1(w,p,[],[],a,[],[],[],gA,[],lp,[])

Network Use

You can create a standard network that uses learnlv1 with newlvq. To prepare the weights of layer i of a custom network to learn with learnlv1,

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 'learnlv1'. Set each net.layerWeights{i,j}.learnFcn to 'learnlv1'. (Each weight learning parameter property is automatically set to learnlv1's default parameters.)

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

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

Algorithm

learnlv1 calculates the weight change dW for a given neuron from the neuron's input P, output A, output gradient gA, and learning rate LR, according to the LVQ1 rule, given i, the index of the neuron whose output a(i) is 1:

dw(i,:) = +lr*(p-w(i,:)) if gA(i) = 0;= -lr*(p-w(i,:)) if gA(i) = -1