Handwritten Digit Recognition using Convolutional Neural Networks (99.04%) and Artificial Neural Networks (93.07%) in Python with Keras and Tensorflow.
The MNIST database (Modified National Institute of Standards and Technology database) of handwritten digits consists of a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger set available from NIST. Additionally, the black and white images from NIST were size-normalized and centered to fit into a 28x28 pixel bounding box and anti-aliased, which introduced grayscale levels.
Python3 with following modules installed
- numpy
- seaborn
- tensorflow
- keras