PureML: a transparent NumPy-only deep learning framework for teaching and prototyping

Python Submitted 02 December 2025Published 23 January 2026
Review

Editor: @espottesmith (all papers)
Reviewers: @sampottinger (all reviews), @paquiteau (all reviews), @Manishms18 (all reviews), @yewentao256 (all reviews)

Authors

Yehor Mishchyriak (0009-0001-8371-7159)

Citation

Mishchyriak, Y., (2026). PureML: a transparent NumPy-only deep learning framework for teaching and prototyping. Journal of Open Source Software, 11(117), 9631, https://doi.org/10.21105/joss.09631

@article{Mishchyriak2026, doi = {10.21105/joss.09631}, url = {https://doi.org/10.21105/joss.09631}, year = {2026}, publisher = {The Open Journal}, volume = {11}, number = {117}, pages = {9631}, author = {Mishchyriak, Yehor}, title = {PureML: a transparent NumPy-only deep learning framework for teaching and prototyping}, journal = {Journal of Open Source Software} }
Copy citation string · Copy BibTeX  
Tags

python numpy autodiff machine-learning deep-learning education

Altmetrics
Markdown badge

 

License

Authors of JOSS papers retain copyright.

This work is licensed under a Creative Commons Attribution 4.0 International License.

Creative Commons License

Table of Contents
Public user content licensed CC BY 4.0 unless otherwise specified.
ISSN 2475-9066