learnp (Neural Network Toolbox)

Perceptron weight/bias learning function

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

[db,LS] = learnp(b,ones(1,Q),Z,N,A,T,E,gW,gA,D,LP,LS)

info = learnp(code)

learnp is the perceptron weight/bias learning function.

learnp(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 = [].

and returns,

dW - S x R weight (or bias) change matrix.

LS - New learning state.

learnp(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.

Examples

Here we define a random input P and error E to a layer with a 2-element input and 3 neurons.

p = rand(2,1);
e = rand(3,1);

Since learnp only needs these values to calculate a weight change (see algorithm below), we will use them to do so.

dW = learnp([],p,[],[],[],[],e,[],[],[],[],[])

You can create a standard network that uses learnp with newp.

To prepare the weights and the bias of layer i of a custom network to learn with learnp:

1.: Set net.trainFcn to 'trainwb'. (net.trainParam will automatically become trainwb's default parameters.)

2.: Set net.adaptFcn to 'adaptwb'. (net.adaptParam will automatically become trainwb's default parameters.)

3.: Set each net.inputWeights{i,j}.learnFcn to 'learnp'. Set each net.layerWeights{i,j}.learnFcn to 'learnp'. Set net.biases{i}.learnFcn to 'learnp'. (Each weight and bias learning parameter property will automatically become the empty matrix since learnp has no learning parameters.)

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

See newp for adaption and training examples.

learnp calculates the weight change dW for a given neuron from the neuron's input P and error E according to the perceptron learning rule:

dw =  0,  if e =  0
=  p', if e =  1
= -p', if e = -1

This can be summarized as:

dw = e*p'