Handwritten Digits Recognition Model

• This is a ML model created using the MNIST-Database

• The MNIST database of handwritten digits, available from this page, has 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. The digits have been size-normalized and centered in a fixed-size image.

• The images in the database have already been pre-formatted and pre-processed, thus, making it a really good beginner friendly ML Project. Link to MNIST Database

• This model has been created using Keras with Tensorflow backend. It is trained for 32 epochs receiving an accuracy of 0.992900013923645(99.2%).

• To use this mode, you must have Jupyter notebook installed(you can also use Google Colaboratory for the same).