learnis

Instar weight learning function

Syntax

[dW,LS] = learnis(W,P,Z,N,A,T,E,gW,gA,D,LP,LS)
info = learnis('code')

Description

learnis is the instar weight learning function.

[dW,LS] = learnis(W,P,Z,N,A,T,E,gW,gA,D,LP,LS) takes several inputs,

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

and returns

 dW S-by-R weight (or bias) change matrix LS New learning state

Learning occurs according to learnis’s learning parameter, shown here with its default value.

 LP.lr - 0.01 Learning rate

info = learnis('code') returns useful information for each code character vector:

 '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 learnis only needs these values to calculate a weight change (see “Algorithm” below), use them to do so.

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

Network Use

To prepare the weights and the bias of layer i of a custom network so that it can learn with learnis,

1. Set net.trainFcn to 'trainr'. (net.trainParam automatically becomes trainr’s default parameters.)

3. Set each net.inputWeights{i,j}.learnFcn to 'learnis'.

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

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

1. Set net.trainParam (net.adaptParam) properties to desired values.

Algorithms

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

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

References

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