MNIST Handwritten digit recognition in keras
The MNIST dataset is one of the most common datasets used for image classification and accessible from many different sources.
The MNIST database contains 60,000 training images and 10,000 testing images taken from American Census Bureau employees and American high school students
I referred to a blog post by Gregor Koehler for this project
Click here for the blog post used
The model trained for this project consists of one input layer, one hidden layer and one softmax output layer. The model is trained over 20 epochs using the Adam optimization method
The model gave a test accuracy of 98%