Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 16 min ago
PreprintarXiv licencearXiv

Build Your Own Neural Network From Scratch

  • Samantha Donner
  • Ethan Geary
  • Peter March
  • Mathew Umano
Open at sourcePDFDOICite

Abstract

These notes are based on our reading of Michael Nielsen's online book neuralnetworksanddeeplearning.com. They represent our effort to elaborate his exposition of neural networks and to provide supporting mathematical detail. Our goal is to provide self-contained instructions for building a basic neural network in the form of pseudocode, so that an interested reader can build a network from scratch and know why it works. No prior knowledge of neural networks or of Python is assumed. Some familiarity with linear algebra, calculus, and probability is helpful but we explain the relevant mathematics in a set of appendices designed to be accessible to newcomers.

Related

  1. How to Bake a Composition Operator from Scratch
    Michael R Pilla
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  2. Vector valued Jack polynomials from scratch
    Charles F. Dunkl, Jean-Gabriel Luque
    Symmetry, Integrability and Geometry : Methods and ApplicationsPeer-reviewedCC BY-NC-SA 4.0Full textCombinatorics & discrete mathematicsHAL
  3. A diffusion-free multi-layer neural-network method for multidimensional nonlinear hyperbolic equations
    Emmanuel Lorin, Arian Novruzi
    arXivPreprintarXiv licenceFull textAnalysis & PDEsNumerical analysis & scientific computingarXiv
  4. Neural Ideals and Neural Codes: An Algebraic Framework for Neural Network Classification and Feature Interpretation
    Venkata Subbaiah Yerrapati, Rahul Dixit, Ajay Kumar Shukla
    arXivPreprintCC BY 4.0Full textAlgebra & number theoryarXiv
  5. Boundary-preserving randomized neural network methods for Poisson equations on general two- and three-dimensional domains
    Huifang Zhou
    arXivPreprintCC BY 4.0Full textNumerical analysis & scientific computingarXiv

Cite

BibTeXRIS
BibTeX
@misc{donner2026build,
  title = {{Build Your Own Neural Network From Scratch}},
  author = {Samantha Donner and Ethan Geary and Peter March and Mathew Umano},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.24271},
  eprint = {2610.24271},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.24271},
}
RIS
TY  - UNPB
TI  - Build Your Own Neural Network From Scratch
AU  - Samantha Donner
AU  - Ethan Geary
AU  - Peter March
AU  - Mathew Umano
PY  - 2026
DA  - 2026/10/16
PB  - arXiv
DO  - 10.48550/arxiv.2610.24271
UR  - https://arxiv.org/abs/2610.24271
AB  - These notes are based on our reading of Michael Nielsen's online book neuralnetworksanddeeplearning.com. They represent our effort to elaborate his exposition of neural networks and to provide supporting mathematical detail. Our goal is to provide self-contained instructions for building a basic neural network in the form of pseudocode, so that an interested reader can build a network from scratch and know why it works. No prior knowledge of neural networks or of Python is assumed. Some familiarity with linear algebra, calculus, and probability is helpful but we explain the relevant mathematics in a set of appendices designed to be accessible to newcomers.
ER  -