English

Self-adaptive node-based PCA encodings

Neural and Evolutionary Computing 2017-08-16 v1 Machine Learning Software Engineering

Abstract

In this paper we propose an algorithm, Simple Hebbian PCA, and prove that it is able to calculate the principal component analysis (PCA) in a distributed fashion across nodes. It simplifies existing network structures by removing intralayer weights, essentially cutting the number of weights that need to be trained in half.

Keywords

Cite

@article{arxiv.1708.04498,
  title  = {Self-adaptive node-based PCA encodings},
  author = {Leonard Johard and Victor Rivera and Manuel Mazzara and JooYoung Lee},
  journal= {arXiv preprint arXiv:1708.04498},
  year   = {2017}
}
R2 v1 2026-06-22T21:15:06.463Z