English

A SOM-based Gradient-Free Deep Learning Method with Convergence Analysis

Machine Learning 2022-01-27 v2

Abstract

As gradient descent method in deep learning causes a series of questions, this paper proposes a novel gradient-free deep learning structure. By adding a new module into traditional Self-Organizing Map and introducing residual into the map, a Deep Valued Self-Organizing Map network is constructed. And analysis about the convergence performance of such a deep Valued Self-Organizing Map network is proved in this paper, which gives an inequality about the designed parameters with the dimension of inputs and the loss of prediction.

Keywords

Cite

@article{arxiv.2101.05612,
  title  = {A SOM-based Gradient-Free Deep Learning Method with Convergence Analysis},
  author = {Shaosheng Xu and Jinde Cao and Yichao Cao and Tong Wang},
  journal= {arXiv preprint arXiv:2101.05612},
  year   = {2022}
}

Comments

there is some little typing err in parameter setting part, which may mislead readers

R2 v1 2026-06-23T22:09:51.518Z