Foundations of Modern Machine Learning

1 Unit · Graduate

This course introduces the theoretical foundations and practical implementation of machine learning methods, with an emphasis on modern algorithmic developments. The curriculum spans classical statistical learning techniques?including regression, classification, regularization, and clustering?as well as contemporary deep learning architectures such as feedforward and convolutional neural networks, recurrent models, and transformers. Core algorithmic principles, including backpropagation, optimization, regularization, and representation learning, are developed both analytically and through software implementation. Students engage with the material through coding-based projects and by examining the computational foundations of large-scale language models.