🧠 CIFAR-10 Image Classification using ANN and CNN

This project demonstrates the implementation and comparison of Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN) for image classification on the CIFAR-10 dataset — a popular benchmark dataset consisting of 60,000 32×32 color images across 10 object categories.

🚀 Project Overview

The goal of this project is to train deep learning models that can classify images into one of 10 categories: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck.

Two models were implemented:

ANN (Fully Connected Neural Network) — a baseline model for quick experimentation.

CNN (Convolutional Neural Network) — designed to better capture spatial features in images.

After training, the CNN achieved a ~69% test accuracy, showing significant improvement over the ANN’s ~44%.