Handwritten digit recognition with simple Neural Net

Version 1.0.0 (11.9 MB) by Lyes Demri
This is a very basic example of handwritten digit recognition using a simple 3-layer neural network built from scratch. Shows every step.
672 Downloads
Updated 4 Oct 2022

View License

This is a very basic example of handwritten digit recognition using a simple 3-layer neural network built from scratch. All steps are implemented, no black box.
MLP.m is the training and testing algorithm
written_digit_recognition.m is a demo of the best trained network (provided) recognizing the digit written in a file you create. Draw a digit with your favorite image editor, save it next to the script, and it will open it and recognize the digit you've written.

Cite As

Lyes Demri (2025). Handwritten digit recognition with simple Neural Net (https://uk.mathworks.com/matlabcentral/fileexchange/118545-handwritten-digit-recognition-with-simple-neural-net), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2009a
Compatible with any release
Platform Compatibility
Windows macOS Linux
Tags Add Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes
1.0.0