NeuralNet.learn

Train neural network on some data, using specified gradient callback and optimizer.

void learn(D data, S delegate(R net_out, ref T ex, ref V[] grad) grad_f, O opt, bool verbose, uint num_cores)
class NeuralNet
void
learn
(
D
T
V
R
S
O : Optimizer
)
(
D data
,
S delegate
(
R net_out
,
ref T ex
,
ref V[] grad
)
grad_f
,
O opt
,
bool verbose = false
,
uint num_cores = 1
)
if (
isForwardRange!D &&
is(ElementType!D == T)
&&
(
is(V == float) ||
is(V == SparseF)
)
&&
(
is(R == float[]) ||
is(R == NeuralNet)
)
&&
(
isNumeric!S ||
is(S == void)
)
)
void learn(D data, string loss, O opt, bool verbose, uint num_cores, bool monitor_loss)
void learn(D data, float delegate(R net_out, ref T ex, ref V[] grad) grad_f, bool verbose, uint num_cores)
void learn(D data, string loss, bool verbose, uint num_cores)

Parameters

data D: forward range of rows
grad_f S delegate ( R net_out , ref T ex , ref V[] grad ): gradient callback (see losses.d for details)
opt O: optimizer to use on all learnable layers for training
verbose bool: whether or not to show progress during training
num_cores uint: degree of Hogwild parallelism