NetworkLayer (Joone API)

java.lang.Object
- org.joone.engine.Layer
- - org.joone.structure.NetworkLayer

All Implemented Interfaces:

java.io.Serializable, java.lang.Runnable, Learnable, LearnableLayer, NeuralLayer, Inspectable
```
public class NetworkLayer
extends Layer
```
Wraps an existing joone network into a single layer. Probably should use something like a Synapse subclass in stead. Will probably run into trouble using Layer, which has a fixed number of input and output rows. Synapse at least has different input and outputs. Maybe should just implement input and output pattern listener.... Will revisit at some stage in the future, for now, Layer at least allows for easy testing. Joone treats input layers funny in that it adds a randomly initialised bias to the input before passing it on. Thus if you use a tanh layer and have say 3 inputs, y1, y2 and y3, then the values passed on to the next (hidden) layer will be [ tanh( y1 + b1 ), tanh( y2 + b2 ), tanh( y3 + b3 ) ] where b1 .. b3 are (random) biases. At the node level, we need more nodes to properly cater for this. New nodes z1 .. z3 are formed where z1 = y1 + b1 or, if e.g. a tanh layer, then z1 = tanh( y1 + b1 ). Thus z1 is a new node, fed from two connections, the first to the actual input and the next to the bias.

Author:

mg

See Also:
Serialized Form

Field Summary

Fields
Modifier and Type	Field and Description
`protected java.util.List<ContextNode>`	`contextNodes` List of all context nodes
`protected boolean`	`fixed` True if context node are in fixed state - useful when simulating
`protected java.util.List<InputNode>`	`inputNodes` List of input nodes
`protected DirectSynapse`	`inputSynapse` Synapse used to interrogate network
`protected java.util.List<Node>`	`nodeList` List of all nodes
`protected java.util.List<java.util.List<Node>>`	`orderedNodes` Ordered nodes
`protected java.util.List<Node>`	`outputNodes` List of output nodes
`protected int`	`patternCount` Pattern counter

Fields inherited from class org.joone.engine.Layer
bias, gradientInps, gradientOuts, inps, inputPatternListeners, learnable, learning, m_batch, monitor, myLearner, outputPatternListeners, outs, running, step, STOP_FLAG

Constructor Summary

Constructors
Constructor and Description

NetworkLayer(NeuralNet network)
Constructor

Constructors
Constructor and Description
`NetworkLayer(NeuralNet network)` Constructor

Method Summary

Methods
Modifier and Type	Method and Description
`protected void`	`backward(double[] pattern)` Reverse transfer function of the component.
`protected void`	`forward(double[] pattern)` Transfer function to recall a result on a trained net
`java.util.List<ContextNode>`	`getContextNodes()` Return a list of all context nodes
`double`	`getDefaultState()` Return the default state of a node in this layer, such as 0 for a tanh or 0.5 for a sigmoid layer
`double`	`getDerivative(int i)` Return the derivative with respect to the function value at a given index.
`java.util.List<InputNode>`	`getInputNodes()` Return a list of all input nodes
`double`	`getMaximumState()` Return maximum value of a node in this layer
`double`	`getMinimumState()` Return minimum value of a node in this layer
`java.util.List<Node>`	`getNodeList()` Return a list of all nodes
`java.util.List<java.util.List<Node>>`	`getOrderedNodes()` Return the ordered nodes
`java.util.List<Node>`	`getOutputNodes()` Return a list of output nodes
`double[]`	`interrogate(double[] pattern)` Interrogate the net
`boolean`	`isFixed()` See if the network is currently in fixed state
`static void`	`main(java.lang.String[] args)` Test
`protected void`	`setDimensions()` Sets the dimension of the layer.
`void`	`setFixed(boolean fixed)` Set state of context nodes.

Methods inherited from class org.joone.engine.Layer
addInputSynapse, addNoise, addOutputSynapse, adjustSizeToFwdPattern, adjustSizeToRevPattern, check, checkInputEnabled, checkInputs, checkOutputs, copyInto, finalize, fireFwdGet, fireFwdPut, fireRevGet, fireRevPut, fwdRun, getAllInputs, getAllOutputs, getBias, getDimension, getLastGradientInps, getLastGradientOuts, getLastInputs, getLastOutputs, getLayerName, getLearner, getMonitor, getRows, getThreadMonitor, hasStepCounter, init, initLearner, InspectableTitle, Inspections, isInputLayer, isOutputLayer, isRunning, join, randomize, randomizeBias, randomizeWeights, removeAllInputs, removeAllOutputs, removeInputSynapse, removeListener, removeOutputSynapse, resetInputListeners, revRun, run, setAllInputs, setAllOutputs, setBias, setConnDimensions, setInputDimension, setInputSynapses, setLastInputs, setLastOutputs, setLayerName, setMonitor, setOutputDimension, setOutputSynapses, setRows, start, stop, sumBackInput, sumInput, toString

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

- Field Detail
  - nodeList
```
protected java.util.List<Node> nodeList
```
    List of all nodes
  - inputNodes
```
protected java.util.List<InputNode> inputNodes
```
    List of input nodes
  - outputNodes
```
protected java.util.List<Node> outputNodes
```
    List of output nodes
  - contextNodes
```
protected java.util.List<ContextNode> contextNodes
```
    List of all context nodes
  - orderedNodes
```
protected java.util.List<java.util.List<Node>> orderedNodes
```
    Ordered nodes
  - fixed
```
protected boolean fixed
```
    True if context node are in fixed state - useful when simulating
  - patternCount
```
protected int patternCount
```
    Pattern counter
  - inputSynapse
```
protected DirectSynapse inputSynapse
```
    Synapse used to interrogate network
- Constructor Detail
  - NetworkLayer
```
public NetworkLayer(NeuralNet network)
```
    Constructor
- Method Detail
  - getDefaultState
```
public double getDefaultState()
```
    Description copied from class: Layer
    
    Return the default state of a node in this layer, such as 0 for a tanh or 0.5 for a sigmoid layer
    
    Specified by:
    
    getDefaultState in class Layer
  - getMinimumState
```
public double getMinimumState()
```
    Description copied from class: Layer
    
    Return minimum value of a node in this layer
    
    Specified by:
    
    getMinimumState in class Layer
  - getMaximumState
```
public double getMaximumState()
```
    Description copied from class: Layer
    
    Return maximum value of a node in this layer
    
    Specified by:
    
    getMaximumState in class Layer
  - backward
```
protected void backward(double[] pattern)
                 throws JooneRuntimeException
```
    Description copied from class: Layer
    
    Reverse transfer function of the component.
    
    Specified by:
    
    backward in class Layer
    
    Parameters:
    pattern - input pattern on which to apply the transfer function
    
    Throws:
    
    JooneRuntimeException
  - forward
```
protected void forward(double[] pattern)
                throws JooneRuntimeException
```
    Description copied from class: Layer
    
    Transfer function to recall a result on a trained net
    
    Specified by:
    
    forward in class Layer
    
    Parameters:
    pattern - input pattern to which to apply the rtransfer function
    
    Throws:
    
    JooneRuntimeException
  - setDimensions
```
protected void setDimensions()
```
    Description copied from class: Layer
    
    Sets the dimension of the layer. Override to define how the internal buffers must be sized.
    
    Specified by:
    
    setDimensions in class Layer
  - getDerivative
```
public double getDerivative(int i)
```
    Description copied from class: Layer
    
    Return the derivative with respect to the function value at a given index. MG: Added for RTRL purposes
    
    Specified by:
    
    getDerivative in class Layer
  - setFixed
```
public void setFixed(boolean fixed)
```
    Set state of context nodes. Context nodes are normally not fixed, so as new data passes through them they will update their internal state with that. If one wants to fix the network to a point in time and examine, without changing the internal state, the impact of different inputs, then one should fix the network. This message allows for that.
  - isFixed
```
public boolean isFixed()
```
    See if the network is currently in fixed state
  - interrogate
```
public double[] interrogate(double[] pattern)
```
    Interrogate the net
  - main
```
public static void main(java.lang.String[] args)
```
    Test
  - getNodeList
```
public java.util.List<Node> getNodeList()
```
    Return a list of all nodes
  - getInputNodes
```
public java.util.List<InputNode> getInputNodes()
```
    Return a list of all input nodes
  - getOutputNodes
```
public java.util.List<Node> getOutputNodes()
```
    Return a list of output nodes
  - getContextNodes
```
public java.util.List<ContextNode> getContextNodes()
```
    Return a list of all context nodes
  - getOrderedNodes
```
public java.util.List<java.util.List<Node>> getOrderedNodes()
```
    Return the ordered nodes

Class NetworkLayer

Field Summary

Fields inherited from class org.joone.engine.Layer

Constructor Summary

Method Summary

Methods inherited from class org.joone.engine.Layer

Methods inherited from class java.lang.Object

Field Detail

nodeList

inputNodes

outputNodes

contextNodes

orderedNodes

fixed

patternCount

inputSynapse

Constructor Detail

NetworkLayer

Method Detail

getDefaultState

getMinimumState

getMaximumState

backward

forward

setDimensions

getDerivative

setFixed

isFixed

interrogate

main

getNodeList

getInputNodes

getOutputNodes

getContextNodes

getOrderedNodes