Deep Learning Neural Network - Digits Recognition Using Keras

This project is to build a Sequential Convolutional Neural Network model for digits recognition trained on MNIST dataset using Keras API.

Project Goal

To correctly identify digits from a dataset of tens of thousands of handwritten images

Source of dataset

Kaggle: https://www.kaggle.com/c/digit-recognizer/data

Introduction

The data files train.csv and test.csv contain gray-scale images of hand-drawn digits, from zero through nine.

Prerequisites

Python and Jupyter Notebook

Author

Lee Ping Tay

Acknowledgement

Adapted from Yassine Ghouzam https://www.kaggle.com/yassineghouzam/introduction-to-cnn-keras-0-997-top-6/notebook