Results 131 to 140 of about 209,957 (232)

Equivariant neural networks and piecewise linear representation theory [PDF]

open access: yesarXiv
Equivariant neural networks are neural networks with symmetry. Motivated by the theory of group representations, we decompose the layers of an equivariant neural network into simple representations. The nonlinear activation functions lead to interesting nonlinear equivariant maps between simple representations.
arxiv  

Decomposition of Equivariant Maps via Invariant Maps: Application to Universal Approximation under Symmetry [PDF]

open access: yesTransactions on Machine Learning Research, 2024
In this paper, we develop a theory about the relationship between invariant and equivariant maps with regard to a group $G$. We then leverage this theory in the context of deep neural networks with group symmetries in order to obtain novel insight into their mechanisms. More precisely, we establish a one-to-one relationship between equivariant maps and
arxiv  

Equivariant Surgery Theory: Construction of Equivariant Normal Maps

open access: yesPublications of the Research Institute for Mathematical Sciences, 1995
This procedure is one of the important ideas of equivariant surgery theory, and has enabled us to construct various exotic actions (see e.g. [BMol-2], [LaMo], [LaMoPa], [Mo 1-3], [MoU], [Pel-3], [PeR]). A method for (Step I) was presented by T. Petrie in [Pel-3], which we call the equivariant transversality construction.
openaire   +3 more sources

A topological model for partial equivariance in deep learning and data analysis. [PDF]

open access: yesFront Artif Intell, 2023
Ferrari L   +3 more
europepmc   +1 more source

Home - About - Disclaimer - Privacy