parameters file for relu act after deepstrom layer + expe on big subsample with thin w matrix + variability check on little subsamples

renaming old scripts for building command line arrays or gathering results -> now useless or moved to scikit-luc

unrelevant changes related to experiments. build_command_line_array shouldn't bu used anymore + changes in drawgraphes relative to cifar10 experiment

moving the fastfood layer to scikit luc + change usage of mnist and cifar datasets in deepfriedconvnetcifar10 and mnsi

timeit now reset graph after each graph execution in order to be fair between functions + add of reshape_x + conv_x + reshape_subsample + conv_subsample + correct mistake on reshape_subsample + conv_subsample + now the results are relevants

scripts for the experiments (run networks, build command lines for networks run, gather oar results, draw graphes from raw results, nystrom vs deepstrom example)

change in the dataset preprocessing + the nystrom layer has now only one matrix W instead of D and V

removed diagonal implementation of fastfood (only hadamard product version remaining) + implementation of the stacked fastfood for the hadamard product version - need command line execution support and then it will be good