vectorflow.layers

Implementation of the various computational layers.

Members

Classes

DenseData
class DenseData

Input layer representing a dense float[]

DropOut
class DropOut

DropOut layer accepting all dense or all sparse parents.

Linear
class Linear

Linear layer accepting sparse or dense parents and outputing a dense vector.

ReLU
class ReLU

ReLU activation layer accepting dense parents.

SeLU
class SeLU

Scaled Exponential Linear Unit activation layer accepting dense parents. See Self-Normalizing Neural Networks for details.

SparseData
class SparseData

Input layer representing a sparse array SparseF[] of (uint, float) pairs

SparseKernelExpander
class SparseKernelExpander

On-the-fly polynomial kernel expansion of sparse input.

TanH
class TanH

TanH activation layer accepting dense parents.

Meta