Differentiable Pooling for Hierarchical Feature Learning

CoRR, 2012.

Cited by: 9|Bibtex|Views122
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We introduce a parametric form of pooling, based on a Gaussian, which can be optimized alongside the features in a single global objective function. By contrast, existing pooling schemes are based on heuristics (e.g. local maximum) and have no clear link to the cost function of the model. Furthermore, the variables of the Gaussian expli...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments