Boston Housing Price Analysis using Regression
Performed predictive modeling on the Boston Housing dataset using Python and scikit-learn. Applied linear regression algorithms, handled data preprocessing, implemented train-test splits, and evaluated model accuracy using Mean Squared Error (MSE) and R² score. Visualized regression results to interpret housing price trends and model performance.
Tech Stack: Python, Pandas, NumPy, scikit-learn, Matplotlib
MNIST Handwritten Digit Classification using CNN
Developed a Convolutional Neural Network (CNN) to classify handwritten digits using the MNIST dataset. Built and trained a deep CNN model with multiple convolutional and pooling layers, applied Softmax activation for multi-class output, and optimized model accuracy using cross-entropy loss and Adam optimizer. Visualized training and validation accuracy and loss to assess model performance.
Tech Stack: Python, TensorFlow, Keras, NumPy, Matplotlib
CIFAR-10 Image Classification using CNN
Designed and trained a Convolutional Neural Network (CNN) to classify images from the CIFAR-10 dataset. Preprocessed and augmented image data to improve model generalization, implemented convolutional, pooling, and fully connected layers, and optimized performance using advanced training callbacks. Evaluated results with confusion matrix and accuracy metrics.
Tech Stack: Python, PyTorch, OpenCV, NumPy, Matplotlib