scalation.modeling.neuralnet.NeuralNet_XLT
See theNeuralNet_XLT companion class
The NeuralNet_XLT companion object provides factory methods for creating multi-layer (one+ hidden layers) neural networks supporting transfer learning. Note, 'scale' is defined in Scaling.
Attributes
Companion
class
Graph
Reset zoom Hide graph Show graph
Supertypes
class Object
trait Matchable
class Any
Self type
Members list
Create a NeuralNet_XLT for a combined data matrix.
Create a NeuralNet_XLT for a combined data matrix.
Value parameters
col
the first designated response column (defaults to the last column)
f
the array of activation function families over all layers
fname
the feature/variable names
hparam
the hyper-parameters
l_tran
the layer to be transferred in (defaults to first hidden layer)
nz
the number of nodes in each hidden layer, e.g., Array (5, 10) means 2 hidden with sizes 5 and 10
transfer
the saved network parameters from a layer of a related neural network
xy
the combined input and output matrix
Attributes
Set the scale flag to the given value.
Set the scale flag to the given value.
Value parameters
scale_
the new value for the scale flag
Attributes
Inherited from:
Scaling
The 'scale' flag indicated whether the data is to be rescaled/normalized
The 'scale' flag indicated whether the data is to be rescaled/normalized
Attributes
Inherited from:
Scaling