case classBatchNormalizationTransform[FV](size: Int, useBias: Boolean, inner: Transform[FV, DenseVector[Double]]) extends Transform[FV, DenseVector[Double]] with Product with Serializable
Implements batch normalization from
http://arxiv.org/pdf/1502.03167v3.pdf
Basically, each unit is shifted and rescaled per minibatch so that its activations
have mean 0 and variance 1. This has been demonstrated to help training deep networks,
but doesn't seem to help here.
Linear Supertypes
Product, Equals, Transform[FV, DenseVector[Double]], Serializable, Serializable, AnyRef, Any
case classLayer(bias: DenseVector[Double], size: Int, innerLayer: Transform.Layer) extends Transform.Layer[FV, DenseVector[Double]] with Product with Serializable
Value Members
final def!=(arg0: Any): Boolean
Definition Classes
AnyRef → Any
final def##(): Int
Definition Classes
AnyRef → Any
final def==(arg0: Any): Boolean
Definition Classes
AnyRef → Any
final defasInstanceOf[T0]: T0
Definition Classes
Any
defclipHiddenWeightVectors(weights: DenseVector[Double], norm: Double, outputLayer: Boolean): Unit
Implements batch normalization from http://arxiv.org/pdf/1502.03167v3.pdf Basically, each unit is shifted and rescaled per minibatch so that its activations have mean 0 and variance 1. This has been demonstrated to help training deep networks, but doesn't seem to help here.