Notes on Hierarchical Splines, DCLNs and i-theory
Author(s)Poggio, Tomaso; Rosasco, Lorenzo; Shashua, Amnon; Cohen, Nadav; Anselmi, Fabio
MetadataShow full item record
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.
Center for Brains, Minds and Machines (CBMM)
CBMM Memo Series;037
i-theory, Deep Convolutional Learning Networks (DCLNs), Networks
The following license files are associated with this item: