MNIST handwritten digit recognition problem and deep learning models developed in Python using the Keras library that are capable of achieving excellent results.
Working Steps: to load the MNIST dataset in Keras and generate plots of the dataset. to reshape the MNIST dataset and develop a simple but well performing multi-layer perceptron model on the problem. to use Keras to create convolutional neural network models for MNIST. to develop and evaluate larger CNN models for MNIST capable of near world class results.
Tools: KERAS,Artificial Neural Network (ANN),CNN Accuracy:99.1%