search

christianbuck / miniNN

Small and simple neural network implementation for research
0 stars 0 forks source link

Handle dense real-valued input data #4

Open 0xtob opened 11 years ago

0xtob commented 11 years ago

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?

christianbuck commented 11 years ago

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.