I m wondering if it is possible to use deep autoencoders (stacked RBMs) for one class classification? Given the dataset is highly biased (95% normal and 5% anomalies ).

asked Dec 18 '13 at 20:22

Sarerf's gravatar image

Sarerf
1111

Be the first one to answer this question!
toggle preview

powered by OSQA

User submitted content is under Creative Commons: Attribution - Share Alike; Other things copyright (C) 2010, MetaOptimize LLC.