the example restarts correctly.

--HG--
rename : examples/dnn_mnist_advanced_ex.cpp => examples/dnn_introduction2_ex.cpp
rename : examples/dnn_mnist_ex.cpp => examples/dnn_introduction_ex.cpp

progress" estimate.  I also renamed the get/set functions for the shrink amount
to have a consistent name and use the word "factor" instead of "amount".

object as an input.  This allows the solvers to exhibit a more complex behavior
that depends on the specific layer.  It also removes the learning rate from the
solver's parameter set and pushes it entirely into the core training code.
This also removes the need for the separate "step size" which previously was
multiplied with the output of the solvers.

Most of the code is still the same, and in the core and trainer the step_size
variables have just been renamed to learning_rate.  The dnn_trainer's relevant
member functions have also been renamed.

The examples have been updated to reflect these API changes.  I also cleaned up
the resnet definition and added better downsampling.

non-one based strides.

- Made layer() recurse into repeat objects so that the index given to layer()
  does what you would expect.
- Added an operator<< for network objects that prints the network architecture.

thing to do for this kind of training.

--HG--
rename : examples/dnn_mnist_resnet_ex.cpp => examples/dnn_mnist_advanced_ex.cpp

to automatically select the right mode.  The serialization format for bn_
layers has also changed, but the code will still be able to deserialize older
bn_ objects.

to template arguments.  This way, the type of a network specifies the entire
network architecture and most of the time the user doesn't even need to do
anything with layer constructors.

amount of time.

--HG--
rename : examples/dnn_mit67_ex.cpp => examples/dnn_mnist_resnet_ex.cpp