Input (aika 0.7 API)

java.lang.Object
- org.aika.Input

All Implemented Interfaces:

Comparable<Input>
```
public class Input
extends Object
implements Comparable<Input>
```
The Input class is just a helper class which is used to initialize a neuron. Most of the parameters of this class will be mapped to a input synapse for this neuron.

Author:

Lukas Molzberger

Nested Class Summary

Nested Classes
Modifier and Type Class and Description

static class Input.RangeRelation

Nested Classes
Modifier and Type	Class and Description
`static class`	`Input.RangeRelation`

Field Summary

Fields
Modifier and Type	Field and Description
`Integer`	`absoluteRid`
`Range.Mapping`	`endMapping`
`Range.Operator`	`endRangeMatch`
`boolean`	`endRangeOutput`
`double`	`maxLowerWeightsSum`
`double`	`minInput`
`Neuron`	`neuron`
`boolean`	`optional`
`boolean`	`recurrent`
`Integer`	`relativeRid`
`Range.Mapping`	`startMapping`
`Range.Operator`	`startRangeMatch`
`boolean`	`startRangeOutput`
`double`	`weight`

Constructor Summary

Constructors
Constructor and Description

Input()

Constructors
Constructor and Description
`Input()`

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`int`	`compareTo(Input in)`
`Input`	`setAbsoluteRid(Integer absoluteRid)` If the absolute relational id (rid) not null, then it is required to match the rid of input activation.
`Input`	`setEndRangeMapping(Range.Mapping endMapping)` Using this method the range begin of the input activation might be mapped to the range end of the output activation.
`Input`	`setEndRangeMatch(Range.Operator rm)` If set to true then the range end of this inputs activation needs to match.
`Input`	`setEndRangeOutput(boolean ro)` Determines if this input is used to compute the range end of the output activation.
`Input`	`setMaxLowerWeightsSum(double maxLowerWeightsSum)` MaxLowerWeightsSum is the expected sum of all weights smaller then the current weight.
`Input`	`setMinInput(double minInput)` The minimum activation value that is required for this input.
`Input`	`setNeuron(Neuron neuron)` Determines the input neuron.
`Input`	`setOptional(boolean optional)` If optional is set to true, then this input is an optional part of a conjunction.
`Input`	`setRangeMatch(Input.RangeRelation rr)` `setRangeMatch` is just a convenience function to call both `setStartRangeMatch` and `setEndRangeMatch` at the same time.
`Input`	`setRangeOutput(boolean ro)` `setRangeOutput` is just a convenience function to call `setStartRangeOutput` and `setEndRangeOutput` at the same time.
`Input`	`setRecurrent(boolean recurrent)` The property `recurrent` specifies if input is a recurrent feedback link.
`Input`	`setRelativeRid(Integer relativeRid)` The relative relational id (rid) determines the relative position of this inputs rid with respect to other inputs of this neuron.
`Input`	`setStartRangeMapping(Range.Mapping startMapping)` Using this method the range end of the input activation might be mapped to the range begin of the output activation.
`Input`	`setStartRangeMatch(Range.Operator rm)` If set to true then the range begin of this inputs activation needs to match.
`Input`	`setStartRangeOutput(boolean ro)` Determines if this input is used to compute the range start of the output activation.
`Input`	`setWeight(Double weight)` The synapse weight of this input.

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

- Field Detail
  - recurrent
```
public boolean recurrent
```
  - optional
```
public boolean optional
```
  - neuron
```
public Neuron neuron
```
  - weight
```
public double weight
```
  - maxLowerWeightsSum
```
public double maxLowerWeightsSum
```
  - minInput
```
public double minInput
```
  - startRangeMatch
```
public Range.Operator startRangeMatch
```
  - endRangeMatch
```
public Range.Operator endRangeMatch
```
  - startRangeOutput
```
public boolean startRangeOutput
```
  - endRangeOutput
```
public boolean endRangeOutput
```
  - startMapping
```
public Range.Mapping startMapping
```
  - endMapping
```
public Range.Mapping endMapping
```
  - relativeRid
```
public Integer relativeRid
```
  - absoluteRid
```
public Integer absoluteRid
```
- Constructor Detail
  - Input
```
public Input()
```
- Method Detail
  - setRecurrent
```
public Input setRecurrent(boolean recurrent)
```
    The property recurrent specifies if input is a recurrent feedback link. Recurrent feedback links can be either negative or positive depending on the weight of the synapse. Recurrent feedback links kind of allow to use future information as inputs of a current neuron. Aika allows this by making assumptions about the recurrent input neuron. The class SearchNode modifies these assumptions until the best interpretation for this document is found.
    
    Parameters:
    
    recurrent -
    
    Returns:
  - setOptional
```
public Input setOptional(boolean optional)
```
    If optional is set to true, then this input is an optional part of a conjunction. This parameter is only used as input for the method createAndNeuron.
    
    Parameters:
    
    optional -
    
    Returns:
  - setNeuron
```
public Input setNeuron(Neuron neuron)
```
    Determines the input neuron.
    
    Parameters:
    
    neuron -
    
    Returns:
  - setMaxLowerWeightsSum
```
public Input setMaxLowerWeightsSum(double maxLowerWeightsSum)
```
    MaxLowerWeightsSum is the expected sum of all weights smaller then the current weight. It is used as an hint to compute the boolean representation of this neuron.
    
    Parameters:
    
    maxLowerWeightsSum -
    
    Returns:
  - setWeight
```
public Input setWeight(Double weight)
```
    The synapse weight of this input.
    
    Parameters:
    
    weight -
    
    Returns:
  - setMinInput
```
public Input setMinInput(double minInput)
```
    The minimum activation value that is required for this input. The minInput value is used to compute the neurons bias. It is only applied in the createAndNeuron method and only affects inputs with a positive weight and the optional flag set to false.
    
    Parameters:
    
    minInput -
    
    Returns:
  - setAbsoluteRid
```
public Input setAbsoluteRid(Integer absoluteRid)
```
    If the absolute relational id (rid) not null, then it is required to match the rid of input activation.
    
    Parameters:
    
    absoluteRid -
    
    Returns:
  - setRelativeRid
```
public Input setRelativeRid(Integer relativeRid)
```
    The relative relational id (rid) determines the relative position of this inputs rid with respect to other inputs of this neuron.
    
    Parameters:
    
    relativeRid -
    
    Returns:
  - setStartRangeMatch
```
public Input setStartRangeMatch(Range.Operator rm)
```
    If set to true then the range begin of this inputs activation needs to match.
    
    Returns:
  - setEndRangeMatch
```
public Input setEndRangeMatch(Range.Operator rm)
```
    If set to true then the range end of this inputs activation needs to match.
    
    Returns:
  - setRangeMatch
```
public Input setRangeMatch(Input.RangeRelation rr)
```
    setRangeMatch is just a convenience function to call both setStartRangeMatch and setEndRangeMatch at the same time.
    
    Parameters:
    
    rr -
    
    Returns:
  - setRangeOutput
```
public Input setRangeOutput(boolean ro)
```
    setRangeOutput is just a convenience function to call setStartRangeOutput and setEndRangeOutput at the same time.
    
    Parameters:
    
    ro -
    
    Returns:
  - setStartRangeOutput
```
public Input setStartRangeOutput(boolean ro)
```
    Determines if this input is used to compute the range start of the output activation.
    
    Parameters:
    
    ro -
    
    Returns:
  - setEndRangeOutput
```
public Input setEndRangeOutput(boolean ro)
```
    Determines if this input is used to compute the range end of the output activation.
    
    Parameters:
    
    ro -
    
    Returns:
  - setStartRangeMapping
```
public Input setStartRangeMapping(Range.Mapping startMapping)
```
    Using this method the range end of the input activation might be mapped to the range begin of the output activation. By default the range begin of the input activation is mapped to the range begin of the output activation.
    
    Parameters:
    
    startMapping -
    
    Returns:
  - setEndRangeMapping
```
public Input setEndRangeMapping(Range.Mapping endMapping)
```
    Using this method the range begin of the input activation might be mapped to the range end of the output activation. By default the range end of the input activation is mapped to the range end of the output activation.
    
    Parameters:
    
    endMapping -
    
    Returns:
  - compareTo
```
public int compareTo(Input in)
```
    Specified by:
    
    compareTo in interface Comparable<Input>

Class Input

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

recurrent

optional

neuron

weight

maxLowerWeightsSum

minInput

startRangeMatch

endRangeMatch

startRangeOutput

endRangeOutput

startMapping

endMapping

relativeRid

absoluteRid

Constructor Detail

Input

Method Detail

setRecurrent

setOptional

setNeuron

setMaxLowerWeightsSum

setWeight

setMinInput

setAbsoluteRid

setRelativeRid

setStartRangeMatch

setEndRangeMatch

setRangeMatch

setRangeOutput

setStartRangeOutput

setEndRangeOutput

setStartRangeMapping

setEndRangeMapping

compareTo