scalation.modeling.forecasting.neuralforecasting.RMSNorm
The RMSNorm class will, in computing the output, normalize by dividing by the Root Mean Square (RMS).
Attributes
-
Graph
-
-
Supertypes
-
trait Serializable
trait Product
trait Equals
class Object
trait Matchable
class Any
Show all
Members list
Forward pass: calculate the output of this layer given the values sent to all its neurons: u = W x where W is a weight matrix
Forward pass: calculate the output of this layer given the values sent to all its neurons: u = W x where W is a weight matrix
Value parameters
-
u
-
the input vector to the given layer
Attributes
Attributes
-
Inherited from:
-
Product
Attributes
-
Inherited from:
-
Product