Page Content
concarne
concarne is a lightweight python framework for learning with side information (aka privileged information). concarne implements a variety of different patterns that enable to apply side information. As it builds upon Theano [1] and lasagne [2], you can use neural network structures that you have developed yourself and easily combine them with the side information learning task.
Repository: https://github.com/tu-rbo/concarne [3]
Accompanies paper: Patterns for Learning with Side Information [4]
Maintainers: Sebastian Höfer, Rico Jonschkowski
Research project: Representation Learning [5]
evious/representation_learning/parameter/en/font4/maxhi
lfe/
Zusatzinformationen / Extras
Quick Access:
Schnellnavigation zur Seite über Nummerneingabe
Auxiliary Functions
Copyright TU Berlin 2008