MNIST neural network training and testing

Full code and functions for training and testing a simple neural network to recognize single digits between 0 and 9
3,4K téléchargements
Mise à jour 13 oct. 2019

Afficher la licence

Full code and functions for training and testing a simple neural network to recognize single digits between 0 and 9. The network has two hidden layers with 80 and 60 neurons respectively (easy to change). Accuracy about 97 %. Please comment if you find any better parameters!

How to run:
1. Make sure all the files are in your current folder.
2. Run "digit_train.m" (will probably take about 5-20 minutes depending on your computer).
3.Run "digit_test.m" to test and evaluate your network.

Citation pour cette source

Johannes Langelaar (2025). MNIST neural network training and testing (https://fr.mathworks.com/matlabcentral/fileexchange/73010-mnist-neural-network-training-and-testing), MATLAB Central File Exchange. Extrait(e) le .

Compatibilité avec les versions de MATLAB
Créé avec R2019b
Compatible avec toutes les versions
Plateformes compatibles
Windows macOS Linux
Catégories
En savoir plus sur Deep Learning Toolbox dans Help Center et MATLAB Answers

Community Treasure Hunt

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

Start Hunting!
Version Publié le Notes de version
1.0.0