This package provides an easy way to build and train simple or complex neural networks.
Each module of a network is composed of
Modules and there
are several sub-classes of
Module available: container classes like
Concat , which can contain simple layers like
Reshape, as well as convolutional layers, and transfer
Loss functions are implemented as sub-classes of
Criterion. They are helpful to train neural network on classical tasks.
Common criterions are the
Mean Squared Error criterion implemented in
and the cross-entropy criterion implemented in