Future Work
###########

The following list gives some ideas---in no particular order---for improving
Glimpse in the future.

* The accessibility of the project could be greatly enhanced by integrating
  Glimpse into a general machine learning framework. Ideally, this
  framework would provide a graphical interface for designing and running
  experiments. A good candidate for such a framework is the `Orange
  project`_.

* It would be helpful to have more advanced backends, particularly one
  targeting GPUs. This could probably be written using `PyCUDA`_ or
  `Theano`_. Some code for this exists in old versions of the project, and
  should be dusted off.

* The biggest boost to accessibility of the project could come from a
  graphical user interface, which allows the user to specify arbitrary
  network topologies. This might be done by hacking an interface out of the
  Orange project's workbench code.

* Create an app package for OS X, probably using PyInstaller_ or py2app_.

* Create an integrated GUI for running experiments and analyzing results. As
  an example, this should integrate the plots shown in the `user guide`_. A
  start in this direction has been made using PySide.

* Add an automated loader/downloader for image corpora, similar to the
  mechanism provided by scikit-learn. For example, this should allow the
  user to download and unpack the AnimalDB_ dataset with a single command.

* Add a script to perform classification on many sub-windows of the same
  image. Use the optimization we built for George's thesis.

* Add an iterable interface for joblib.Parallel to support a progress meter.

.. _Orange project: http://orange.biolab.si/
.. _PyCUDA: http://mathema.tician.de/software/pycuda
.. _Theano: http://deeplearning.net/software/theano/
.. _PyInstaller: http://www.pyinstaller.org/
.. _py2app: http://pythonhosted.org/py2app/
.. _AnimalDB: http://cbcl.mit.edu/software-datasets/serre/SerreOlivaPoggioPNAS07/index.htm