Dataset: MNIST Face and Digit Data
Methodology: Employed Naive Bayes, Perceptron, and k Nearest Neighbors to accurately classify handwritten digits (MNIST Dataset) and faces (Pascal Dataset).
Outcome: Achieved a mean accuracy of 82% for Digit data and 90% for Face data, underlining the model's proficiency in recognizing handwritten digits and faces.
This project demonstrates my ability to implement an efficient classification system, utilizing essential tools like Numpy, Matplotlib, Naive Bayes, Perceptron, and k Nearest Neighbors. The impressive accuracy rates of 82% for digits and 90% for faces testify to the approach's effectiveness.