A Matlab implementation of handwritten digit recognition using the MNIST dataset.
This is the neural network implementation of handwritten digit recognition based on Michael Nielsen’s book: Neural Networks and Deep Learning Chapter 1. This matlab code is a modified version of his python code which can be found here.
This program was run in MATLAB 2016b. The main file is digitRecognition.m. In this file, you can configure the number of hidden layers, number of nodes per layers, number of training epochs, learning rate, and the size of the mini batches.