converts the input to numpy arrays

loads the data from the gzip pickled files, and converts to numpy arrays

The main loss function (inner_cca_objective) is wrapped in this function due to the constraints imposed by Keras on objective functions

builds the whole model the structure of each sub-network is defined in build_mlp_net, and it can easily get substituted with a more effic

An implementation of linear CCA # Arguments: H1 and H2: the matrices containing the data for view 1 and view 2. Each row is a sample.

loads and returns the content of a pickled file it handles the inconsistencies between the pickle packages available in Python 2 and 3

trains a linear SVM on the data input C specifies the penalty factor of SVM

produce the new features by using the trained model # Arguments model: the trained model data1 and data2: the train, validation, a

trains the model # Arguments data1 and data2: the train, validation, and test data for view 1 and view 2 respectively. data should be

It is the loss function of CCA as introduced in the original paper. There can be other formulations. It is implemented by Theano tens