| dc.contributor.author | Poggio, Tomaso | |
| dc.contributor.author | Rosasco, Lorenzo | |
| dc.contributor.author | Shashua, Amnon | |
| dc.contributor.author | Cohen, Nadav | |
| dc.contributor.author | Anselmi, Fabio | |
| dc.date.accessioned | 2015-12-11T22:30:52Z | |
| dc.date.available | 2015-12-11T22:30:52Z | |
| dc.date.issued | 2015-09-29 | |
| dc.identifier.uri | http://hdl.handle.net/1721.1/100201 | |
| dc.description.abstract | 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 pooling (sum or max). We discuss how these observations together with i-theory may provide a framework for a general theory of deep networks. | en_US |
| dc.description.sponsorship | This work was supported by the Center for Brains, Minds and Machines (CBMM), funded by NSF STC award CCF - 1231216. | en_US |
| dc.language.iso | en_US | en_US |
| dc.publisher | Center for Brains, Minds and Machines (CBMM) | en_US |
| dc.relation.ispartofseries | CBMM Memo Series;037 | |
| dc.rights | Attribution-NonCommercial 3.0 United States | * |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc/3.0/us/ | * |
| dc.subject | i-theory | en_US |
| dc.subject | Deep Convolutional Learning Networks (DCLNs) | en_US |
| dc.subject | Networks | en_US |
| dc.title | Notes on Hierarchical Splines, DCLNs and i-theory | en_US |
| dc.type | Technical Report | en_US |
| dc.type | Working Paper | en_US |
| dc.type | Other | en_US |
