Handwritten Digits Classifier

Overview

My first machine-learning project — a TensorFlow/Keras CNN trained on the MNIST dataset to recognise handwritten digits 0–9. Built during the AI elective at Delhi Public School, R. K. Puram, and recently cleaned up into a reproducible repo reaching ~99.2% test accuracy in under a minute on CPU. Walks through the full pipeline end-to-end: data loading and normalisation, a two-block Conv → Pool architecture, training, confusion-matrix evaluation, and a single-image prediction CLI.