Hierarchical compositional feature learning

Understand

We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images.

• The building blocks are binary features defined hierarchically as a composition of some of the features in the layer immediately below, arranged in a particular manner.
• At a high level, HCN is similar to a sigmoid belief network with pooling.
• Inference and learning in HCN are very challenging and existing variational approximations do not work satisfactorily.