Mar 12, 2015 · This paper builds upon the basic counting grid model and it shows that hierarchical reasoning helps avoid bad local minima, produces better ...

This paper builds upon the basic counting grid model and it shows that hierarchical reasoning helps avoid bad local minima, produces better classi- fication ...

In the main paper we presented two hierarchical models,. HCG and HCCG; the former is built stacking a CCG and a CG, the latter stacking two CCGs models.

This paper builds upon the basic counting grid model and it shows that hierarchical reasoning helps avoid bad local minima, produces better classification ...

This paper builds upon the basic counting grid model and it shows that hierarchical reasoning helps avoid bad local minima, produces better classification ...

This paper builds upon the basic counting grid model and it shows that hierarchical reasoning helps avoid local minima, produces better classification accuracy ...

This paper builds upon the basic counting grid model and it shows that hierarchical reasoning helps avoid bad local minima, produces better classification ...

This paper builds upon the basic counting grid model and it shows that hierarchical reasoning helps avoid bad local minima, produces better classification ...

Fingerprint. Dive into the research topics of 'Hierarchical learning of grids of microtopics'. Together they form a unique fingerprint.

Nebojsa Jojic, Alessandro Perina, Dongwoo Kim: Hierarchical learning of grids of microtopics. CoRR abs/1503.03701 (2015).