📖 Deep Statistical Learning

👉 Full repository: deep_statistical_learning

I started writing these notes during my master’s degree as a way to organize and clarify my understanding of machine learning and deep learning. Over time, the notes have grown into a comprehensive study resource that combines theoretical foundations with practical insights.

I enjoy organizing knowledge and writing things down, and these notes reflect that process — carefully breaking down concepts, connecting ideas, and recording them in a way that can be revisited and built upon.

🏗️ Deep Learning System Design

👉 Repository: DL System Design

This note is about the practical design of deep learning and LLM-based systems. It focuses on bridging research with production: covering concepts such as scalable architectures, model deployment, monitoring, and system reliability. The aim is to capture design patterns and lessons that make ML/DL services both effective and maintainable.

I welcome all comments and suggestions—and I’d be happy to improve and grow this note together with you.

📐 Matrix Methods

👉 Repository: Matrix Methods

This note collects my study materials on linear algebra and matrix methods, focusing on the concepts most relevant to machine learning and deep learning. It includes explanations, worked examples, and connections between theory and practical applications.

I welcome all comments and suggestions—and I’d be happy to improve and grow this note together with you.

NLP and LLM

👉 Repository: NLP Note

These are my working notes on NLP and large language models: intuitive math, minimal proofs, and practical recipes.

I welcome all comments and suggestions—and I’d be happy to improve and grow this note together with you.

💻 Coding Note

⚠️ This section is temporarily closed while I reorganize and refine the notes.
It will be updated and re-opened later.

This is a collection of tutorial-style study notes on programming. The aim is to make concepts clear, practical, and applicable, with examples that can be adapted to real coding tasks.

📚 Topics

• Agile & Software Development — workflows, methodologies, and best practices
• Algorithms & Computer Science — problem-solving patterns, data structures, and theory
• Programming Languages — C, Go, Python, Rust, SQL
• Machine Learning & Deep Learning — theory notes, implementations, and experiments
• Natural Language Processing (NLP) — applied tutorials and coding exercises
• DevOps & Linux — shell scripts, automation, system tools, and environment setup
• Git & Vim — version control workflows and editor productivity
• Regular Expressions (RegEx) — pattern matching and cheat sheets
• Web Scraping — techniques and scripts for data collection
• Reading Notes (ToReads, KS-Study) — study references and knowledge summaries

I welcome all comments and suggestions—and I’d be happy to improve and grow this note together with you.

📘 Reinforcement Learning Notes

👉 You can check out the full notes here: reinforcement_learning_note

There are already a number of excellent tutorials and lectures on Reinforcement Learning (RL), but I often find that many of them do not provide enough detail or explanation of the formulas behind the concepts. In many cases, key ideas are assumed to be obvious or straightforward—which can be a challenge for someone like me, who has a weaker background in mathematics but still wants a comprehensive understanding of RL.

📊 Statistics

👉 Repository: Statistics

This note collects my study materials on probability and statistics, with a focus on the foundations needed for data science, machine learning, and deep learning. It combines key definitions, derivations, and examples, aiming to make abstract ideas easier to understand and apply.

I welcome all comments and suggestions—and I’d be happy to improve and grow this note together with you.