learncon

(To be removed) Conscience bias learning function

learncon will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Syntax

[dB,LS] = learncon(B,P,Z,N,A,T,E,gW,gA,D,LP,LS)
info = learncon('code')


Description

learncon is the conscience bias learning function used to increase the net input to neurons that have the lowest average output until each neuron responds approximately an equal percentage of the time.

[dB,LS] = learncon(B,P,Z,N,A,T,E,gW,gA,D,LP,LS) takes several inputs,

B	S-by-1 bias vector
P	1-by-Q ones vector
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

dB	S-by-1 weight (or bias) change matrix
LS	New learning state

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

LP.lr - 0.001

Learning rate

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

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

Deep Learning Toolbox™ 2.0 compatibility: The LP.lr described above equals 1 minus the bias time constant used by trainc in the Deep Learning Toolbox 2.0 software.

Examples

Here you define a random output A and bias vector W for a layer with three neurons. You also define the learning rate LR.

a = rand(3,1);
b = rand(3,1);
lp.lr = 0.5;

Because learncon only needs these values to calculate a bias change (see “Algorithm” below), use them to do so.

dW = learncon(b,[],[],[],a,[],[],[],[],[],lp,[])

Network Use

To prepare the bias of layer i of a custom network to learn with learncon,

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

2. Set net.adaptFcn to 'trains'. (net.adaptParam automatically becomes trains’s default parameters.)

3. Set net.inputWeights{i}.learnFcn to 'learncon'

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

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

1. Set net.trainParam (or net.adaptParam) properties as desired.

2. Call train (or adapt).

Algorithms

learncon calculates the bias change db for a given neuron by first updating each neuron’s conscience, i.e., the running average of its output:

c = (1-lr)*c + lr*a

The conscience is then used to compute a bias for the neuron that is greatest for smaller conscience values.

b = exp(1-log(c)) - b

(learncon recovers C from the bias values each time it is called.)

Version History

Introduced before R2006a

R2026a: learncon will be removed

learncon will be removed in a future release.

To learn more about customizing training algorithms, see these examples and topics:

• Custom Training Loops

• Define Custom Learning Rate Schedule

• Train Network Using Custom Training Loop

• Compare Custom Solvers Using Custom Training Loop

• Speed Up Deep Neural Network Training

• Accelerate Custom Training Loop Functions

• Evaluate Deep Learning Experiments by Using Metric Functions

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.