Frames No Frames Cognitoware API v2009512
Cognitoware.Robotics.dll

Class LikelihoodMap<X, Y>
X: The type predicated by the distribution.
Y: The type on which the predictions depend.

System.Object
Cognitoware.Mathematics.Probability.RandomConditional<X>
Cognitoware.Mathematics.Probability.LikelihoodMap<X, Y>

## Summary

A conditional distribution that maps likelihood functions over Y to distinct values of X.

## Constructor Summary

Creates an empty conditional distribution.

## Method Summary

BayesianInference(X, RandomDistribution<Y>)
Inherited from Cognitoware.Mathematics.Probability.RandomConditional
ConditionalProbabilityOf(X, Y)
Calculate the conditional probability for a value of X given a known value of Y.
ConditionBy(Y)
Creates a probability distribution over X conditioned on a specific value of Y.
Equals(Object)
Inherited from System.Object
Finalize()
Inherited from System.Object
GetHashCode()
Inherited from System.Object
GetType()
Inherited from System.Object
LikelihoodOf(X)
Returns the function describing the likelihood of all values of Y being observed given the fact that result is observed.
Marginalize(RandomDistribution<Y>)
Not implemented in LikelihoodMap.
MemberwiseClone()
Inherited from System.Object
Set(X, RandomDistribution<Y>)
Maps a distribution over Y to a value of X.
ToString()
Inherited from System.Object

## Details

ConditionalMap contains a dictionary that maps discrete values of Y to distributions of X. X is required to be discrete. Y may be continuous or discrete. The functions over Y are not necessarily normalized.

## Constructor Details

public LikelihoodMap()
Creates an empty conditional distribution.

## Method Details

public override Double ConditionalProbabilityOf(X x, Y y)
This method returns the probability of result being observed given the fact that you know range is observed. It simply looks up the distribution associated with result and asks it for the probability of range. An exception will be thrown if no distribution is found mapped to result. This method implements the abstract declaration in RandomConditional.

### Parameters:

`x` - The value in X.
`y` - The conditional value in Y.

### Returns:

The probability of result conditioned on range.

public override RandomDistribution<X> ConditionBy(Y y)
Creates a probability distribution over X given a known value y.

### Parameters:

`y` - The value of Y over which the conditional distribution.

### Returns:

The probability of X given the specific value of Y.

public override RandomDistribution<Y> LikelihoodOf(X x)
Returns the distribution of Y that is mapped to the specific value of result. An exception is thrown if there is no distribution mapped to result.

### Parameters:

`x` - A fixed value in X.

### Returns:

A likelihood function as a RandomDistribution. Because the returned value is not normalized, it is a likelihood function and not a distribution.

public override RandomDistribution<X> Marginalize(RandomDistribution<Y> y)
This method throws a NotImplementedException.

public void Set(X x, RandomDistribution<Y> y)
Maps a distribution over Y to a value of X.

### Parameters:

`x` - The value of X to map to the likelihood function.
`y` - The likelihood function to map to X.