Notes on Hierarchical Splines, DCLNs and i-theory
Name
CBMM-Memo-037.pdf
Size
1.83 MB
Format
Adobe PDF
Checksum (MD5)
10d88001e33d4f39bc21fb939aee3acb
Author(s)
Poggio, Tomaso
Rosasco, Lorenzo
Shashua, Amnon
Cohen, Nadav
Anselmi, Fabio
Date Issued
September 29, 2015
Publisher
Center for Brains, Minds and Machines (CBMM)
Series/Report no.
CBMM Memo Series;037
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.
Subjects
i-theory
Deep Convolutional Learning Networks (DCLNs)
Networks
Terms of Use
Attribution-NonCommercial 3.0 United States
Persistent DSpace Link
