edu.stanford.nlp.math

## Class DoubleAD

• All Implemented Interfaces:
Serializable

public class DoubleAD
extends Number
The class DoubleAD was created to extend the current calculations of gradient to automatically include a calculation of the Hessian vector product with another vector v. This is used with the Stochastic Meta Descent Optimization, but could be extended for use in any application that requires an additional order of differentiation without explicitly creating the code.
Version:
2006/12/06
Author:
Alex Kleeman
See Also:
Serialized Form
• ### Constructor Detail

• #### DoubleAD

public DoubleAD()
• #### DoubleAD

public DoubleAD(double initVal,
double initDot)
• ### Method Detail

• #### equals

public boolean equals(Object obj)
Overrides:
equals in class Object
• #### equals

public boolean equals(double valToCompare,
double dotToCompare)
• #### equals

public boolean equals(double valToCompare,
double dotToCompare,
double TOL)
• #### getval

public double getval()
• #### getdot

public double getdot()
• #### set

public void set(double value,
double dotValue)
• #### setval

public void setval(double a)
• #### setdot

public void setdot(double a)
• #### plusEqualsConst

public void plusEqualsConst(double a)
• #### plusEquals

public void plusEquals(DoubleAD a)
• #### minusEquals

public void minusEquals(DoubleAD a)
• #### minusEqualsConst

public void minusEqualsConst(double a)
• #### doubleValue

public double doubleValue()
Specified by:
doubleValue in class Number
• #### floatValue

public float floatValue()
Specified by:
floatValue in class Number
• #### intValue

public int intValue()
Specified by:
intValue in class Number
• #### longValue

public long longValue()
Specified by:
longValue in class Number
• #### hashCode

public int hashCode()
Overrides:
hashCode in class Object

Stanford NLP Group