Neural Networks as Linear Regression: An Introduction for Statisticians

Abigail Loe, Susan Murray, Zhenke Wu
6/22/2026
stat.MLcs.LG

No confident code implementation found for this paper.

Abstract

Neural networks are a commonly used prediction tool in computer science and statistics. However, the barrier to entry of this interesting field remains high, particularly for classical statisticians trained in a frequentist perspective. In this letter, we demystify neural networks by describing networks that approximate a linear regression and describe common customizations that provide a foundation for further study.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Six Lectures on Linearized Neural Networks

83% match2023

Nonparametric regression with modified ReLU networks

83% match2022

Deep Learning and Symbolic Regression for Discovering Parametric Equations

83% match1 repo102022

A Statistical-Modelling Approach to Feedforward Neural Network Model Selection

82% match2022

A Novel Paradigm for Neural Computation: X-Net with Learnable Neurons and Adaptable Structure

81% match2024

ParaRNN: An Interpretable and Parallelizable Recurrent Neural Network for Time-Dependent Data

81% match2026

Cite this paper

@article{loe2026neural,
  title  = {Neural Networks as Linear Regression: An Introduction for Statisticians},
  author = {Abigail Loe and Susan Murray and Zhenke Wu},
  year   = {2026},
  eprint = {2606.23601},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2606.23601v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2606.23601.svg)](https://codeofpaper.com/paper/2606.23601)

Discussion