Constraint

public abstract class Constraint

Known Direct Subclasses MaxNorm, MinMaxNorm, NonNeg, UnitNorm MaxNorm Constrains the weights incident to each hidden unit to have a norm less than or equal to a desired value.  MinMaxNorm Constrains the weights to have the norm between a lower bound and an upper bound.  NonNeg Constrains the weights to be non-negative.  UnitNorm Constrains the weights to have unit norm.

Base class for Constraints. Constraint subclasses impose constraints on weight values

Constants

float

EPSILON

Public Constructors

Constraint(Ops tf) Creates a Constraint

Public Methods

abstract <T extends TNumber> Operand<T>	call(Operand<T> weights) Applies the constraint against the provided weights
Ops	getTF() Gets the TensorFlow Ops

Inherited Methods

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

Constants

public static final float EPSILON

Constant Value: 1.0E-7

Public Constructors

public Constraint (Ops tf)

Creates a Constraint

Parameters

tf	the TensorFlow Ops

Public Methods

public abstract Operand<T> call (Operand<T> weights)

Applies the constraint against the provided weights

Parameters

weights	the weights

Returns

• the constrained weights

public Ops getTF ()

Gets the TensorFlow Ops

Returns

• the TensorFlow Ops