Holomorphic feedforward networks
Abstract
A very popular model in machine learning is the feedforward neural network (FFN). The FFN can approximate general functions and mitigate the curse of dimensionality. Here we introduce FFNs which represent sections of holomorphic line bundles on complex manifolds, and ask some questions about their approximating power. We also explain formal similarities between the standard approach to supervised learning and the problem of finding numerical Ricci flat Kähler metrics, which allow carrying some ideas between the two problems.
 Publication:

arXiv eprints
 Pub Date:
 May 2021
 arXiv:
 arXiv:2105.03991
 Bibcode:
 2021arXiv210503991D
 Keywords:

 Mathematics  Complex Variables;
 High Energy Physics  Theory;
 Mathematics  Numerical Analysis;
 32Q25
 EPrint:
 13 pages, version to appear in PAMQ