LeCun

public class LeCun

LeCun normal initializer.

Draws samples from a random distribution. * *

If the distribution is TRUNCATED_NORMAL, it draws samples from a truncated normal distribution centered on 0 with stddev = sqrt(1 / fanIn) where fanIn is the number of input units in the weight tensor.

If the distribution is UNIFORM, itraws samples from a uniform distribution within [-limit, limit], where limit = Math.sqrt(3 / fanIn) (fanIn is the number of input units in the weight tensor)

Examples:

LeCun Normal:

      long seed = 1001l;
      LeCunNormal<TFloat32, TFloat32> initializer =
              new org.tensorflow.framework.initializers.LeCunNormal<>(tf,
               Distribution.TRUNCATED_NORMAL, seed);
      Operand<TFloat32> values =
              initializer.call(tf.constant(Shape.of(2,2)), TFloat32.class);
 

LeCun Uniform:

      long seed = 1001l;
      LeCunNormal<TFloat32, TFloat32> initializer =
              new org.tensorflow.framework.initializers.LeCunNormal<>(tf,
               Distribution.UNIFORM, seed);
      Operand<TFloat32> values =
              initializer.call(tf.constant(Shape.of(2,2)), TFloat32.class);
 

*

NOTE: *

For a LeCunNormal equivalent initializer, use TRUNCATED_NORMAL for the distribution parameter. *

For a LeCunUniform equivalent initializer, use UNIFORM * for the distribution parameter. *

See Also

• ERROR(href="https://papers.nips.cc/paper/6698-self-normalizing-neural-networks">Self-Normalizing Neural Networks, Klambauer et al., 2017/Self-Normalizing Neural Networks, Klambauer et al., 2017)
• Efficient Backprop, Lecun et al., 1998
• VarianceScaling.Distribution

Inherited Constants

From class org.tensorflow.framework.initializers.VarianceScaling

double

SCALE_DEFAULT

Inherited Fields

From class org.tensorflow.framework.initializers.VarianceScaling

public static final VarianceScaling.Distribution	DISTRIBUTION_DEFAULT
public static final VarianceScaling.Mode	MODE_DEFAULT

Public Constructors

LeCun(Ops tf, VarianceScaling.Distribution distribution, long seed) Creates a LeCunNormal Initializer

Inherited Methods

From class org.tensorflow.framework.initializers.VarianceScaling

Operand<T>

call(Operand<TInt64> dims, Class<T> type)

From class org.tensorflow.framework.initializers.BaseInitializer

Ops	getTF() Gets the TensorFlow Ops

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()

From interface org.tensorflow.framework.initializers.Initializer

abstract Operand<T>

call(Operand<TInt64> dims, Class<T> type) Generates the operation used to perform the initialization.

Public Constructors

public LeCun (Ops tf, VarianceScaling.Distribution distribution, long seed)

Creates a LeCunNormal Initializer

Parameters

tf	the TensorFlow Ops
distribution	The distribution type for the Glorot initializer.
seed	the seed for random number generation. An initializer created with a given seed will always produce the same random tensor for a given shape and dtype.