Dog Species Classification Using Logistic Regression and KNN with 65%+ Accuracy

Implemented a machine learning solution for dog species classification using Logistic Regression and K-Nearest Neighbors (KNN) on the Stanford Dogs Dataset. The project involved preprocessing image and categorical data, extracting features, and tuning hyperparameters for optimal performance. Achieved over 65% classification accuracy by leveraging the complementary strengths of Logistic Regression for linear separability and KNN for handling complex patterns. This project demonstrated proficiency in working with real-world datasets and delivering interpretable results in the domain of animal species recognition.