Inspired by @kencoken's commit f36e715
kencoken@f36e715

Related issues:

 rather than zero in the feature binarization example

definitions appropriately

backward pass to compute analytic gradient (the thing being checked) now

but apparently not)

forward

Feature extraction, feature binarization and image retrieval examples

- signficantly change the documentation file
- link to it from index.md
- remove the image resizing script, since (a) it does not work, (b) is obviated by using ImagesLayer
- add sample prototxt that uses ImagesLayer.

fix script path incantation
convert css indentation to spaces
fix cifar10 leveldb creation path
wget without checking certificate for dropbox (dodge complaint on linux)
docs: added list of contributors
minor style update of docs

Compute loss in the forward pass

…layer

Loss in forward pass fix for window data layer

- examples, test and pycaffe compile without problem (matcaffe not tested)
- tests show some errors (on cpu gradient tests), to be investigated
- random generators need to be double checked
- mkl commented code needs to be removed

[shelhamer: removed math function tests, since they were merged via
other branches]

previously filled in all NaNs for me, making many tests fail)

1)

issue: #79

add MKL dirs conditioned on USE_MKL
include libraries before making LD_FLAGS

They were the wrong way round, causing linking to fail in some cases

This ensures that it works with ATLAS's header file, which doesn't include such
a guard itself (whereas the reference version from Ubuntu's libblas-dev does)

The FIXMEs about RNG were addressed by caffe_nextafter for
uniform distributions and the normal distribution concern is surely a
typo in the boost documentation, since the normal pdf is correctly
stated elsewhere in the documentation.

Split boost random number generation from the common Caffe singleton and
add a helper function for rng. This resolves a build conflict in OSX
between boost rng and nvcc compilation of cuda code.

Refer to #165 for a full discussion.

Thanks to @satol for suggesting a random number generation facade rather
than a total split of cpp and cu code, which is far more involved.

The exact details of the contributions are recorded by versioning.

MKL/non-MKL Reconciliation

Caffe no longer requires MKL. By default it builds without it, relying on atlas and cblas instead. Set the `USE_MKL` var in your Makefile.config accordingly.

Hdf5 output layer

Add more convenience math functions and all tests pass