In order to apply miniNN to vision tasks like USPS or to traditional data mining challenges, it would be necessary to allow for dense real-valued input data. How hard would this be?
Very simple! Just make a class Corpus from which both sparsecorpus and densecorpus are derived. The training for dense data, i.e. updating the gradient pretty much already in there.
In order to apply miniNN to vision tasks like USPS or to traditional data mining challenges, it would be necessary to allow for dense real-valued input data. How hard would this be?