CNN_1D

scalation.modeling.neuralnet.CNN_1D
See theCNN_1D companion class
object CNN_1D

The CNN_1D companion object provides factory methods for creating 1D convolutional neural networks.

Attributes

Companion
class
Graph
Supertypes
class Object
trait Matchable
class Any
Self type
CNN_1D.type

Members list

Value members

Concrete methods

def apply(xy: MatrixD): CNN_1D
def updateParam(x_: MatrixD, z: MatrixD, δ0: MatrixD, δ1: MatrixD, eta: Double, c: VectorD, b: NetParam): Unit

Update the parameters: the weights in the convolutional filter c and the weights biases in the fully-connected layer b.

Update the parameters: the weights in the convolutional filter c and the weights biases in the fully-connected layer b.

Value parameters

b

the fully-connectd layer parameters

c

the convolution filter vector

x_

the training/full data/input matrix

z

the training/full response/output matrix

δ0

the convolutional layer delta

δ1

the fully-connectd layer delta

Attributes