Instance Constructors
-
new
RbmStack(rbms: List[Rbm])
Value Members
-
final
def
!=(arg0: AnyRef): Boolean
-
final
def
!=(arg0: Any): Boolean
-
final
def
##(): Int
-
final
def
==(arg0: AnyRef): Boolean
-
final
def
==(arg0: Any): Boolean
-
final
def
asInstanceOf[T0]: T0
-
def
clone(): AnyRef
-
final
def
eq(arg0: AnyRef): Boolean
-
def
equals(arg0: Any): Boolean
-
def
finalize(): Unit
-
final
def
getClass(): Class[_]
-
def
hashCode(): Int
-
final
def
isInstanceOf[T0]: Boolean
-
final
def
ne(arg0: AnyRef): Boolean
-
final
def
notify(): Unit
-
final
def
notifyAll(): Unit
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
-
def
toImage: BufferedImage
-
def
toImage(w: Int, h: Int): BufferedImage
-
def
toImage(colormap: (Double) ⇒ Int): BufferedImage
-
def
toString(): String
-
-
-
final
def
wait(): Unit
-
final
def
wait(arg0: Long, arg1: Int): Unit
-
final
def
wait(arg0: Long): Unit
Inherited from AnyRef
Inherited from Any
Encapsulates training procedures for stacks of Rbm's. The Rbm's must be stored in the following way: the innermost Rbm of the future autoencoder (or: the top Rbm of the stack) must be the last element of the list. The Rbm at the bottom, which is clamped to the input, must be the first element. It's assumed that all dimensions of the Rbm's are compatible. Please keep in mind that the signals are stored in row-vectors, which are propagated by multiplication from the right by the weight matrices.