Abstract | ||
---|---|---|
Product models of low dimensional experts are a powerful way to avoid the curse of dimensionality. We present the "undercomplete product of experts" (UPoE), where each expert models a one dimensional projection of the data. The UPoE may be interpreted as a parametric probabilistic model for projection pursuit. Its ML learning rules are identical to the approximate learning rules proposed before for under-complete ICA. We also derive an efficient sequential learning algorithm and discuss its relationship to projection pursuit density estimation and feature induction algorithms for additive random field models. |
Year | Venue | Keywords |
---|---|---|
2012 | UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence | projection pursuit,product model,undercomplete product,low dimensional expert,dimensional projection,additive random field model,efficient parametric projection pursuit,expert model,approximate learning rule,projection pursuit density estimation,efficient sequential,density estimation |
DocType | Volume | ISBN |
Journal | abs/1212.2513 | 0-127-05664-5 |
Citations | PageRank | References |
1 | 1.32 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Max Welling | 1 | 4875 | 550.34 |
Richard S. Zemel | 2 | 4958 | 425.68 |
geoffrey e hinton | 3 | 40435 | 4751.69 |