edu.stanford.nlp.math
Class DoubleAD
java.lang.Object
java.lang.Number
edu.stanford.nlp.math.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 a additional order of differentiation without explicitly creating the code.
- Author:
- Alex Kleeman
- See Also:
- Serialized Form
DoubleAD
public DoubleAD()
DoubleAD
public DoubleAD(double initVal,
double initDot)
equals
public boolean equals(DoubleAD b)
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
toString
public String toString()
- Overrides:
toString
in class Object
Stanford NLP Group