Machine learning projects.

• Adaptive Boosting: Implemented from scratch. Uses Logistic Regression as a weak learner. Performance is evaluated on the Telco dataset, Credit card dataset and Adult dataset from Kaggle. Note: the datasets are zipped.
• FNN: Feed-forward Neural Network implemented from scratch. Performance is evaluated using the EMNIST dataset (digits identification).
• GMM: - Principal Component Analysis (PCA) for reducing the dimensions of sample data. - Implementation of the Expectation-Maximization (EM) algorithm to estimate the Gaussian Mixture Model (GMM).