MNIST neural network training and testing

Version 1.0.0 (14.2 MB) by Johannes Langelaar
Full code and functions for training and testing a simple neural network to recognize single digits between 0 and 9
4.9
(7)
2.9K Downloads
Updated 13 Oct 2019

View License

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.

Cite As

Johannes Langelaar (2024). MNIST neural network training and testing (https://www.mathworks.com/matlabcentral/fileexchange/73010-mnist-neural-network-training-and-testing), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2019b
Compatible with any release
Platform Compatibility
Windows macOS Linux
Categories
Find more on Deep Learning Toolbox in Help Center and MATLAB Answers

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