This repository is structured to support progressive learning and deep exploration across different areas of machine learning. It includes:
- Classical ML: Traditional machine learning algorithms such as regression, clustering, dimensionality reduction, and time series models.
- Mathematics: Notes and code covering linear algebra, calculus, statistics, and optimization crucial for understanding ML fundamentals.
- Neural Networks (NN): Core deep learning architectures, including foundational deep neural networks and recurrent models.
- Convolutional Neural Networks (CNN): Specialized neural network structures focused on visual data processing, with notes, code, and experiments.
- Case Studies and Class Notes: Curated notes, recorded lectures, and detailed class materials supporting theory and practical implementations.
- Notebooks: Jupyter notebooks organized by topic to experiment and practice concepts interactively.
- Links: Collections of curated external resources such as research papers, video lectures, and tutorials.