CIFAR-10 Image Classification
Overview

This project implements and compares four machine learning models to classify images from the CIFAR-10 dataset into 10 categories:

   1. Naive Bayes
   2. Decision Tree
   3. Multi-Layer Perceptron (MLP)
   4. Convolutional Neural Network (CNN - VGG11)

The models are evaluated using accuracy, Feature extraction using a pre-trained ResNet-18 model and dimensionality reduction using PCA are employed to improve performance for certain models.

Dataset

-The CIFAR-10 dataset contains 60,000 RGB images of size 32x32
    Training Data: 500 images
    Test Data: 100 images

Results (Best)

Model	           Accuracy	
Naive Bayes	     79.10%	    
Decision Tree	  59.10%	    
MLP	           82.00%	    
CNN (VGG11)	     84.14%	    

Acknowledgments

Dataset: CIFAR-10
Libraries: PyTorch, Scikit-learn, Matplotlib, Numpy