Convolutional Neural Network for Recognizing Handwritten Digits
Aim: The aim of the "Digit Recognizer" project is to build a prediction model that can predict the value of handwritten digits.
Input set: The training data set has 785 columns. The first column, called "label", is the digit that was drawn by the user. The rest of the columns contain the pixel-values of the associated image.
Output set: For each of the 28000 images in the test set, there is a single line containing the ImageId and the digit predicted by the model.
Approach: This project uses the Convolutional Neural Network approach to build the prediction model. The CNN model is implemented using the Keras module.
Link to all dataset: https://www.kaggle.com/c/digit-recognizer/data
Compiled by Shreyash Gupta.