NeuralLayer

Abstract base class of all layers in the net.

Members

Properties

learnable
bool learnable [@property getter]

whether or not this layer has any parameters to be learnt

Variables

backgrads
float[][] backgrads;

array of gradients to backpropagate to parents

children
NeuralLayer[] children;

array referencing all the children of this layer

dim_in
size_t dim_in;

total input dimension of this layer (sum of output dimensions of its parents)

dim_out
size_t dim_out;

total output dimension of this layer

name
string name;
out_d
float[] out_d;

dense output vector of this layer (might be unused)

out_s
SparseF[] out_s;

sparse output vector of this layer (might be unused)

parents
NeuralLayer[] parents;

array referencing all the parents of this layer

type
LayerT type;

Meta