Ethen's Notebook Collection

Implements core algorithms like decision trees, gradient boosting, and matrix factorization from scratch, building deep understanding beyond library APIs as highlighted in the README sections.

Spans from basic linear regression to advanced topics like LLMs, reinforcement learning, and time series, evidenced by the extensive documentation listings across multiple domains.

Includes practical examples using FastAPI, Kubernetes, AWS, and Ray for model deployment, preparing learners for real-world scenarios as shown in the model_deployment section.

Hands-on usage of scikit-learn, PyTorch, TensorFlow, and other popular libraries bridges educational and practical skills, with notebooks covering both from-scratch and library-based approaches.