This repository provides executable lecture notes and slides for Cornell's CS5785 Applied Machine Learning course (Fall 2024). It's designed for students and practitioners seeking to understand and implement various machine learning concepts, from foundational supervised and unsupervised learning to advanced deep learning topics like Transformers and LLMs.

How It Works

The course materials are presented as executable Jupyter Notebooks and accompanying slides. This approach allows users to not only read about ML concepts but also to run the code, experiment with parameters, and visualize results directly, fostering a deeper, hands-on understanding of the algorithms and their practical application.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt within a virtual environment.
• Prerequisites: Python environment. Specific package versions are managed by requirements.txt.

Highlighted Details

• Comprehensive coverage from basic ML to advanced deep learning (CNNs, RNNs, Transformers/LLMs).
• Includes practical topics like model diagnosis, error analysis, and bias/variance tradeoff.
• Features guest lectures and a tentative schedule outlining the course progression.
• Executable lecture notes allow for interactive learning and experimentation.

Maintenance & Community

This repository is associated with Cornell University's CS5785 course, maintained by Volodymyr Kuleshov. Feedback is welcomed via email.

Licensing & Compatibility

The repository content is typically licensed under a permissive license (e.g., MIT or Apache) for educational materials, allowing broad use and adaptation. Specific license details are not explicitly stated in the README.

Limitations & Caveats

The materials are specific to the Fall 2024 iteration of the course and may differ from other versions or associated video lectures. Slide and PDF content is subject to updates throughout the semester.