Overview

This documentation is a curated collection of notes, summaries, and core AI/ML concepts that I’ve gathered over the past few years. The goal is to provide a structured, high-quality reference for engineers and researchers who want to deepen their understanding of the field or revisit key foundations with clarity.

Why this exists#

The AI/ML ecosystem evolves quickly, and while large language models (LLMs) and agent systems dominate current discussions, a solid grasp of the underlying principles is still essential for building, evaluating, and scaling modern AI systems. These materials are designed to make it easier to quickly review the “building blocks” behind today’s AI/ML technologies without losing sight of the fundamentals.

Sections#

This collection is organized into major domains, each offering structured notes, summaries, and key takeaways:

• Machine Learning (Work in progress)
• Deep Learning (Planned)
• NLP (Transformers) (Planned)
• CV (Diffusion Models) (Planned)
• Reinforcement Learning (Planned)
• LLM / VLM (Planned)
• Agent Systems (Planned)

Future expansions will broaden the scope of coverage:

• Applied Practices — lessons and design choices from real-world AI/ML applications.

Together, these sections aim to balance technical depth with practical coverage, helping you strengthen your knowledge foundation and stay prepared for both research and applied AI/ML challenges.