Notes on Hierarchical Splines, DCLNs and i-theory
We define an extension of classical additive splines for multivariate function approximation that we call hierarchical splines. We show that the case of hierarchical, additive, piece-wise linear splines includes present-day Deep Convolutional Learning Networks (DCLNs) with linear rectifiers and pool...
| Main Authors: | , , , , |
|---|---|
| פורמט: | Technical Report |
| שפה: | en_US |
| יצא לאור: |
Center for Brains, Minds and Machines (CBMM)
2015
|
| נושאים: | |
| גישה מקוונת: | http://hdl.handle.net/1721.1/100201 |