Dimension reduction in heterogeneous neural networks: Generalized Polynomial Chaos (gPC) and ANalysis-Of-VAriance (ANOVA)

M. Choi, T. Bertalan, C. R. Laing, I. G. Kevrekidis

Research output: Contribution to journalArticle

3 Scopus citations

Abstract

We propose, and illustrate via a neural network example, two different approaches to coarse-graining large heterogeneous networks. Both approaches are inspired from, and use tools developed in, methods for uncertainty quantification (UQ) in systems with multiple uncertain parameters – in our case, the parameters are heterogeneously distributed on the network nodes. The approach shows promise in accelerating large scale network simulations as well as coarse-grained fixed point, periodic solution computation and stability analysis. We also demonstrate that the approach can successfully deal with structural as well as intrinsic heterogeneities.

Original languageEnglish (US)
Pages (from-to)1165-1180
Number of pages16
JournalEuropean Physical Journal: Special Topics
Volume225
Issue number6-7
DOIs
StatePublished - Sep 1 2016

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Physics and Astronomy(all)
  • Physical and Theoretical Chemistry

Fingerprint Dive into the research topics of 'Dimension reduction in heterogeneous neural networks: Generalized Polynomial Chaos (gPC) and ANalysis-Of-VAriance (ANOVA)'. Together they form a unique fingerprint.

  • Cite this