English

Using Linear Regression for Iteratively Training Neural Networks

Machine Learning 2023-07-17 v2

Abstract

We present a simple linear regression based approach for learning the weights and biases of a neural network, as an alternative to standard gradient based backpropagation. The present work is exploratory in nature, and we restrict the description and experiments to (i) simple feedforward neural networks, (ii) scalar (single output) regression problems, and (iii) invertible activation functions. However, the approach is intended to be extensible to larger, more complex architectures. The key idea is the observation that the input to every neuron in a neural network is a linear combination of the activations of neurons in the previous layer, as well as the parameters (weights and biases) of the layer. If we are able to compute the ideal total input values to every neuron by working backwards from the output, we can formulate the learning problem as a linear least squares problem which iterates between updating the parameters and the activation values. We present an explicit algorithm that implements this idea, and we show that (at least for small problems) the approach is more stable and faster than gradient-based methods.

Keywords

Cite

@article{arxiv.2307.05189,
  title  = {Using Linear Regression for Iteratively Training Neural Networks},
  author = {Harshad Khadilkar},
  journal= {arXiv preprint arXiv:2307.05189},
  year   = {2023}
}

Comments

10 pages

R2 v1 2026-06-28T11:26:59.967Z