English

Growing axons: greedy learning of neural networks with application to function approximation

Machine Learning 2020-02-18 v2 Numerical Analysis Numerical Analysis Machine Learning

Abstract

We propose a new method for learning deep neural network models that is based on a greedy learning approach: we add one basis function at a time, and a new basis function is generated as a non-linear activation function applied to a linear combination of the previous basis functions. Such a method (growing deep neural network by one neuron at a time) allows us to compute much more accurate approximants for several model problems in function approximation.

Keywords

Cite

@article{arxiv.1910.12686,
  title  = {Growing axons: greedy learning of neural networks with application to function approximation},
  author = {Daria Fokina and Ivan Oseledets},
  journal= {arXiv preprint arXiv:1910.12686},
  year   = {2020}
}
R2 v1 2026-06-23T11:57:11.257Z