NetCompiler.BooneCompiledNet (boone)

java.lang.Object
- boone.structure.NetCompiler.BooneCompiledNet

All Implemented Interfaces:: NetCompiler.CompiledNet

Enclosing class:: NetCompiler

protected static class NetCompiler.BooneCompiledNet
extends java.lang.Object
implements NetCompiler.CompiledNet

The Boone CompiledNet instance.

Field Summary

Fields
Modifier and Type	Field and Description
`protected Function[]`	`activationFn` Activation function.
`protected double[]`	`bias` Neuron biases.
`protected int`	`calcOrder` Calculation order.
`protected boolean[]`	`directed` Flag whether this link is directed.
`protected double[]`	`externalInput` the external input signal, meant for the input of input neurons.
`protected double[]`	`input` Current input signal.
`protected int[]`	`inputNeurons` Indices of the input neurons, in the correct order.
`protected double[]`	`linkInput` The sum of the inputs from the links to this neuron.
`protected int[]`	`linkSinkNeuron` Sink neurons of the links.
`protected int[]`	`linkSourceNeuron` Source neurons of the links.
`protected boolean[]`	`loopOutputToInput` Loop back output to the linkInput after every cycle? Default: false.
`protected int`	`maxCycles` max number of network cycles, usually just 1.
`protected int`	`numInputNeurons` Number of input neurons.
`protected int`	`numLinks` Number of links.
`protected int`	`numNeurons` Total number of neurons.
`protected int`	`numOutputNeurons` Number of output neurons.
`protected int[][]`	`outLinks` Array of arrays of links from the given neuron to other neurons.
`protected double[]`	`output` Current unit output.
`protected int[]`	`outputNeurons` Indices of the output neurons, in the correct order.
`protected int[]`	`tickList` Tick list, for random calculation order.
`protected boolean[]`	`usingBias` Am I using the bias? Default: true.
`protected double[]`	`value` Link value.
`protected double[]`	`weight` Weight of this link.
`protected boolean`	`zeroInputAfterFirstCycle` Reset the external input of the input neurons to zero after the first cycle when innervating the network? Probably only useful for recurrent networks, where the internal per-neuron feed-back should take over (see `Neuron.loopOutputToInput`).

Constructor Summary

Constructors
Modifier Constructor and Description

protected BooneCompiledNet()

Constructors
Modifier	Constructor and Description
`protected`	`BooneCompiledNet()`

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`protected void`	`calculateNeuron(int neuron)` Calculate the given neuron.
`NetCompiler.CompiledNet`	`compile(NeuralNet net)` Compile the given network into this compiled net.
`double[]`	`getOutput(double[] outputs)` Extract the output pattern from the network.
`void`	`innervate()` Innervate the network.
`protected void`	`innervateCycle(int cycle)` Innervate the network for a single cycle.
`protected void`	`propagateLink(int link, double output, boolean forwardDirection)` Propagate the given link.
`protected void`	`propagateNeuronOutput(int neuron)` Propagate the given neuron's output.
`void`	`setInput(double[] values)` Load the input pattern into the network.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - numNeurons
```
protected int numNeurons
```
    Total number of neurons.
  - numInputNeurons
```
protected int numInputNeurons
```
    Number of input neurons.
  - inputNeurons
```
protected int[] inputNeurons
```
    Indices of the input neurons, in the correct order.
  - numOutputNeurons
```
protected int numOutputNeurons
```
    Number of output neurons.
  - outputNeurons
```
protected int[] outputNeurons
```
    Indices of the output neurons, in the correct order.
  - numLinks
```
protected int numLinks
```
    Number of links.
  - activationFn
```
protected Function[] activationFn
```
    Activation function. default: Function.Sigmoid.
  - usingBias
```
protected boolean[] usingBias
```
    Am I using the bias? Default: true.
  - loopOutputToInput
```
protected boolean[] loopOutputToInput
```
    Loop back output to the linkInput after every cycle? Default: false.
  - bias
```
protected double[] bias
```
    Neuron biases.
  - externalInput
```
protected double[] externalInput
```
    the external input signal, meant for the input of input neurons.
  - linkInput
```
protected double[] linkInput
```
    The sum of the inputs from the links to this neuron. This is calculated step by step in the propagateLink(int, double, boolean) method.
    This is a kind of replacement for the initial activation value in other net models.
  - input
```
protected double[] input
```
    Current input signal. Calculated in the calculateNeuron(int) method by adding the linkInput and the externalInput values.
  - output
```
protected double[] output
```
    Current unit output.
  - outLinks
```
protected int[][] outLinks
```
    Array of arrays of links from the given neuron to other neurons.
  - linkSourceNeuron
```
protected int[] linkSourceNeuron
```
    Source neurons of the links.
  - linkSinkNeuron
```
protected int[] linkSinkNeuron
```
    Sink neurons of the links.
  - weight
```
protected double[] weight
```
    Weight of this link.
  - value
```
protected double[] value
```
    Link value. Specifically, the forward link value.
  - directed
```
protected boolean[] directed
```
    Flag whether this link is directed.
  - maxCycles
```
protected int maxCycles
```
    max number of network cycles, usually just 1. Mostly used for recurrent networks.
  - zeroInputAfterFirstCycle
```
protected boolean zeroInputAfterFirstCycle
```
    Reset the external input of the input neurons to zero after the first cycle when innervating the network? Probably only useful for recurrent networks, where the internal per-neuron feed-back should take over (see Neuron.loopOutputToInput).
    Default: false.
  - calcOrder
```
protected int calcOrder
```
    Calculation order.
  - tickList
```
protected int[] tickList
```
    Tick list, for random calculation order.
- Constructor Detail
  - BooneCompiledNet
```
protected BooneCompiledNet()
```
- Method Detail
  - setInput
```
public void setInput(double[] values)
```
    Load the input pattern into the network.
    
    Specified by:
    
    setInput in interface NetCompiler.CompiledNet
  - innervate
```
public void innervate()
```
    Innervate the network. This implementation is very much like the original one in NeuralNet. Note:
    
    Specified by:
    
    innervate in interface NetCompiler.CompiledNet
  - innervateCycle
```
protected void innervateCycle(int cycle)
```
    Innervate the network for a single cycle.
    
    Parameters:
    
    cycle - the current cycle
  - calculateNeuron
```
protected void calculateNeuron(int neuron)
```
    Calculate the given neuron.
    
    See Also:
    
    Neuron.calculate()
  - propagateNeuronOutput
```
protected void propagateNeuronOutput(int neuron)
```
    Propagate the given neuron's output.
    
    See Also:
    
    Neuron.propagateOutput()
  - propagateLink
```
protected void propagateLink(int link,
                             double output,
                             boolean forwardDirection)
```
    Propagate the given link. See Link.propagate().
  - getOutput
```
public double[] getOutput(double[] outputs)
```
    Extract the output pattern from the network.
    
    Specified by:
    
    getOutput in interface NetCompiler.CompiledNet
    
    Parameters:
    
    outputs - Array to put the outputs into. If too small or null, we allocate a new double array for the values.
  - compile
```
public NetCompiler.CompiledNet compile(NeuralNet net)
                                throws NetCompiler.CompileException
```
    Compile the given network into this compiled net.
    
    Specified by:
    
    compile in interface NetCompiler.CompiledNet
    
    Throws:
    
    NetCompiler.CompileException

Class NetCompiler.BooneCompiledNet

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

numNeurons

numInputNeurons

inputNeurons

numOutputNeurons

outputNeurons

numLinks

activationFn

usingBias

loopOutputToInput

bias

externalInput

linkInput

input

output

outLinks

linkSourceNeuron

linkSinkNeuron

weight

value

directed

maxCycles

zeroInputAfterFirstCycle

calcOrder

tickList

Constructor Detail

BooneCompiledNet

Method Detail

setInput

innervate

innervateCycle

calculateNeuron

propagateNeuronOutput

propagateLink

getOutput

compile