CoFilter_1D

scalation.modeling.neuralnet.CoFilter_1D
See theCoFilter_1D companion class
object CoFilter_1D

The CoFilter_1D object provides the convolution and pooling operators.

Attributes

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

Members list

Value members

Concrete methods

def conv(c: VectorD, x: VectorD): VectorD

Return the 'valid' (no padding) convolution of cofilter c and input vector x. Caveat: does not include reversal.

Return the 'valid' (no padding) convolution of cofilter c and input vector x. Caveat: does not include reversal.

Value parameters

c

the cofilter vector of coefficient

x

the input/data vector

Attributes

def conv(c: VectorD, x: MatrixD): MatrixD

Return the convolution over all data instances.

Return the convolution over all data instances.

Value parameters

c

the cofilter vector of coefficient

x

the input/data matrix

Attributes

def convf(c: VectorD, x: VectorD): VectorD

Return the 'full' convolution of cofilter c and input vector x.

Return the 'full' convolution of cofilter c and input vector x.

Value parameters

c

the cofilter vector of coefficient

x

the input/data vector

Attributes

def convs(c: VectorD, x: VectorD): VectorD

Return the 'same' convolution of cofilter c and input vector x. Same means that the size of the result is the same as the input.

Return the 'same' convolution of cofilter c and input vector x. Same means that the size of the result is the same as the input.

Value parameters

c

the cofilter vector of coefficient

x

the input/data vector

Attributes

def pool(x: VectorD, s: Int): VectorD

Return the max-pooling results over all pooling windows.

Return the max-pooling results over all pooling windows.

Value parameters

s

the the size of the pooling window

x

the input/data vector

Attributes

def pool(x: MatrixD, s: Int): MatrixD

Return the pooling results over all data instances.

Return the pooling results over all data instances.

Value parameters

s

the the size of the pooling window

x

the input/data matrix

Attributes