This will impact the forward and backward methods in:
network type
layer type
dense_layer type
conv2d_layer type
Effectively, rather than looping over sample in a batch inside of network % train, we will pass batches of data all the way down to the lowest level, that is, the forward and backward methods of dense_layer and conv2d_layer types. Lowering the looping over the sample in a batch will also allow the implementation of a batchnorm_layer.
It will also potentially allow more efficient matmuls in dense and conv layers if we replace the stock matmul with some more specialized and efficient sgemm or similar from some flavor of BLAS or MKL.
In support of #155.
This will impact the
forward
andbackward
methods in:network
typelayer
typedense_layer
typeconv2d_layer
typeEffectively, rather than looping over sample in a batch inside of
network % train
, we will pass batches of data all the way down to the lowest level, that is, theforward
andbackward
methods ofdense_layer
andconv2d_layer
types. Lowering the looping over the sample in a batch will also allow the implementation of abatchnorm_layer
.It will also potentially allow more efficient
matmul
s in dense and conv layers if we replace the stockmatmul
with some more specialized and efficientsgemm
or similar from some flavor of BLAS or MKL.