<LLM: Learning by Building from Scratch> Commentary Lecture

We understand why Attention was needed and how it works by 'implementing it directly with code'. This lecture starts from the structural limitations of RNN and Seq2Seq models, experimentally verifies the information bottleneck problem and long-term dependency issues created by fixed context vectors, and naturally explains how Attention emerged to solve these limitations. Rather than simply introducing concepts, we directly confirm RNN's structural limitations and Seq2Seq's information bottleneck problems through experiments, and implement **Bahdanau Attention (additive attention)** and **Luong Attention (dot-product attention)** one by one to clearly understand their differences. Each attention mechanism forms Query–Key–Value relationships in what way, has what mathematical and intuitive differences in the weight calculation process, and why it inevitably led to later models naturally connects to their characteristics and evolutionary flow. We learn how Attention views sentences and words, and how each word receives importance weighting to integrate information in a form where formula → intuition → code → experiment are connected as one. This lecture is a process of building 'foundational strength' to properly understand Transformers, helping you deeply understand why the concept of Attention was revolutionary, and why all subsequent state-of-the-art NLP models (Transformer, BERT, GPT, etc.) adopt Attention as a core component. This lecture is optimized for learners who want to embody the flow from RNN → Seq2Seq → Attention not through concepts but through code and experiments.

You use ChatGPT, but haven’t you found it difficult to explain why it produces answers like these? “I know terms like RAG, agents, and fine-tuning… but it’s difficult to explain them precisely.” “When I hear LLM-related terminology, I’m at a loss for words.” “Explanations of concepts in AI meetings are always vague.” This course was created specifically for people like you. This is a theory course designed to help you understand LLMs not as ‘tools,’ but as ‘structures.’ Rather than teaching you how to use ChatGPT or Gemini, it gives you a framework for explaining why they work the way they do.

"Your first step to creating a customized LLM with LoRA-based lightweight fine-tuning!" This is an introductory hands-on course designed so that even those new to LLMs can easily follow along. We minimize complex theory and guide you step-by-step through the entire process: loading the model → applying data → training → comparing results. In a short time, you'll directly experience the workflow of cutting-edge lightweight fine-tuning techniques like LoRA and QLoRA, and gain an intuitive understanding of "how LLM fine-tuning works." Even without extensive resources, experience the satisfaction of creating an LLM specialized for your domain!

You will learn about Transformers inside out by directly implementing everything from Multi-Head Attention to the Original Transformer model, BERT, the Encoder-Decoder-based MarianMT translation model, and the Vision Transformer in code.

Do you know the basics but feel overwhelmed when it comes to applying them in practice? Drawing on real-world experience, we make complex LLM architectures easy to understand.

This course will teach you the concept of the Google Gemini model and how to use the Gemini API, and create various AI applications using Streamlit.

This course covers the theory and practical examples of LLMs, based on <Fundamentals of Large Language Models, Quickly!> (Insight, 2025).

This introductory course for AI engineers is designed to provide a brief hands-on experience of the entire process, from data processing and model development to cloud, MLOps, and ethical considerations. It focuses on building practical skills by helping students understand the process of connecting models to actual services, rather than just creating them. The course includes hands-on exercises and examples so that even those learning AI for the first time can easily follow along.

This course covers the entire process of evolving ChatGPT from a simple conversational AI into an intelligent AI Agent that performs real-world tasks. By utilizing the three core frameworks—LangChain, LangGraph, and LangSmith—you will build AI Agents that can be used immediately in practice.

Starting with the question, "If I were on the Titanic, would I have survived?", this course completes a full-stack project where you develop an AI model to predict survival probabilities based on real data and deploy it as a web service. You will gain hands-on experience in the entire process of AI and web development, from deep learning modeling using PyTorch to building a backend server with FastAPI and implementing a user interface with Next.js.

We explore how to create an AI judge by combining knowledge graphs, reasoning systems, and various agent frameworks such as CrewAI, LangChain, and AutoGen, which enable the implementation of LLM-based multi-agent technology.

From core theories of deep learning and CNN to various CNN model implementation methods, and practical deep learning development know-how through real-world problems, If you want to become a deep learning CNN technology expert based on Pytorch, join us in this lecture :)

Mastering difficult AI with just one single analogy?! A first step into AI principles, understanding through core concepts rather than just terminology.

We will explore the types of applications and web services that can be built using LLMs.

Build your own powerful stock analysis model that uses AI to analyze over 40 types of economic indicators and stock price data to predict not only the S&P 500 and QQQ ETF, but also individual stocks!

LLM and Agent, the fundamental technologies behind AI like ChatGPT. LLM is currently the technology that has come closest to AGI. In this lecture, we will explore LLM and Agent technologies from a layperson's perspective.