[Complete NLP Mastery II] Dissecting the Transformer Architecture: From Attention Expansion to Full Model Assembly and Training

This course is a hands-on masterclass that completely dissects the core technological evolution of generative AI, from LDM (Latent Diffusion Model) to DiT (Diffusion Transformer). We directly analyze the latent space-based learning principles of LDM, the structure of Stable Diffusion, and the implementation methods of the latest Diffusion Transformer through papers and code. Students will systematically learn the latest trends and structural evolution of generative models by directly implementing LDM, CFG (Classifier-Free Guidance), and DiT models using PyTorch.

This course is a hands-on masterclass that completely conquers the evolution of Diffusion Models through papers and code implementation. You'll learn the core models of generative AI, including DDPM (Denoising Diffusion Probabilistic Model) and DDIM, by studying the paper principles and implementing them directly. We analyze step-by-step the background of each model's emergence, mathematical formulations, network architectures (U-Net, VAE, Transformer), training processes (Noise Schedule, Denoising Step), and the ideas that led to performance improvements. Students will directly code all models using PyTorch, gaining not just paper comprehension but 'practical skills to reproduce and apply' them in real-world scenarios. Additionally, by comparing the differences between models and their developmental flow, you'll clearly understand how they expand and evolve. This course integrates theory, code, and practice into one comprehensive journey, providing researchers, developers, and creators alike with a systematic way to master the evolution of generative models. Beyond simply 'reading' papers, start your experience of 'understanding and recreating' through direct implementation now.

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.

We implement the latest Transformer-based PixArt and lightweight adaptation SANA step by step from theory to code. Building on DDPM·DDIM·LDM·DiT covered in Parts I·II, we complete hands-on practice including text encoder integration, samplers (DDIM/ODE), v-prediction/CFG tuning, and small-scale data style fine-tuning.

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.

This course is a hands-on masterclass that completely conquers the evolution of Diffusion Models through papers and code implementation. You'll learn the core models of generative AI, including DDPM (Denoising Diffusion Probabilistic Model) and DDIM, by studying the paper principles and implementing them directly. We analyze step-by-step the background of each model's emergence, mathematical formulations, network architectures (U-Net, VAE, Transformer), training processes (Noise Schedule, Denoising Step), and the ideas that led to performance improvements. Students will directly code all models using PyTorch, gaining not just paper comprehension but 'practical skills to reproduce and apply' them in real-world scenarios. Additionally, by comparing the differences between models and their developmental flow, you'll clearly understand how they expand and evolve. This course integrates theory, code, and practice into one comprehensive journey, providing researchers, developers, and creators alike with a systematic way to master the evolution of generative models. Beyond simply 'reading' papers, start your experience of 'understanding and recreating' through direct implementation now.

This course covers basic natural language processing techniques and various text tasks using deep learning.

This course is a hands-on program for implementing generative AI applications based on text, images, voice, and documents using the OpenAI API. Starting from setting up the Anaconda and Jupyter Notebook environment, it covers essential development environment configurations for practical work, including API Key management and understanding costs and tokens. Based on the latest Responses API, you'll implement text generation, summarization, classification, Vision (image understanding), voice processing, and PDF input processing, while practicing core features used directly in the field step-by-step, such as Function Calling, Structured Outputs (Pydantic), Embedding, and RAG (File Search). Additionally, including Web Search, Code Interpreter, Streaming, Background tasks, and Conversation State management, you'll learn how to expand beyond simple API calls to 'intelligent AI services'. Finally, the goal is to implement agent-based AI systems that autonomously select and execute tools using the Agents SDK and MCP (Model Context Protocol), while learning the structure and design perspectives necessary for actual service development.

Python Korean Text Analysis and Natural Language Processing: Word Cloud Visualization, Morphological Analysis, Topic Modeling, Clustering, Similarity Analysis, Bag of Words and TF-IDF for Text Data Vectorization, Text Classification Using Machine Learning and Deep Learning, and How to Use Hugging Face

We implement the latest Transformer-based PixArt and lightweight adaptation SANA step by step from theory to code. Building on DDPM·DDIM·LDM·DiT covered in Parts I·II, we complete hands-on practice including text encoder integration, samplers (DDIM/ODE), v-prediction/CFG tuning, and small-scale data style fine-tuning.

RAG (Retrieval-Augmented Generation) from theory to the latest multimodal and agent-based RAG! This is a hands-on lecture designed to be understandable even for non-majors. From paper reviews to practical code implementation, it's designed so that even those encountering RAG for the first time can easily follow along.

Many test takers want to practice past exam questions. Why is that? Because exam creators refer to past exam questions. Solving the latest past exams is the shortcut to passing.

Mastering Model Context Protocol (MCP) is a practical, engineering-focused course designed to help developers build real, secure, and production-ready AI backends. After helping thousands of students overcome confusion around LLM integration, tool calling, and backend architecture, I created this course to solve the most common problems: “How do I build a reliable backend that LLMs can call safely?” “How do I choose between SSE, stdio, or streamable-http?” “How do I scale MCP into real applications with FastAPI, Auth0, and LangGraph?” “How do I structure my MCP tools, resources, prompts, and context?” In this course, I guide you step-by-step—from spinning up a minimal MCP server to deploying a fully secure, Dockerized system. Every lesson is hands-on, designed to remove complexity and give you a clear, repeatable workflow for building modern AI systems. If you're frustrated by vague tutorials and want a clear, concrete, engineering-level understanding of MCP, this course is built for you.

This course is a hands-on masterclass that completely dissects the core technological evolution of generative AI, from LDM (Latent Diffusion Model) to DiT (Diffusion Transformer). We directly analyze the latent space-based learning principles of LDM, the structure of Stable Diffusion, and the implementation methods of the latest Diffusion Transformer through papers and code. Students will systematically learn the latest trends and structural evolution of generative models by directly implementing LDM, CFG (Classifier-Free Guidance), and DiT models using PyTorch.

This is a course covering the GitHub notebooks and bonus content from <Build a Large Language Model from Scratch> (Gilbut, 2025). GitHub: https://github.com/rickiepark/llm-from-scratch/ <Build a Large Language Model from Scratch> is the Korean translation of the bestseller <Build a Large Language Model (from Scratch)> (Manning, 2024) by Sebastian Raschka. This book provides a way to learn and utilize the operating principles of large language models by building a complete model starting from scratch with OpenAI's GPT-2 model.

This introductory course, designed to be the easiest and most practical for Python beginners, covers intuitive dashboards using Streamlit, Google Cloud Platform for deployment, and more. Additionally, you can also prepare for the 빅데이터 분석기사 practical exam.

This is a lecture covering LLM theory and practical examples based on <Large Language Models, Just the Essentials!> (Insight, 2025).

🔥 Vibe Coding with Streamlit 🔥 Real-time coding experience where you can instantly create your own web service with just one line of code! Visual-focused, hands-on lectures tailored to MZ sensibilities - no complex backend knowledge required. Learn the basics of Streamlit and awaken your development instincts by directly implementing practical apps. Complete your own "personal service" with code in a vibe way right now 😎💻

We guide non-majors and beginners to quickly obtain the Big Data Analytics Engineer practical certification! Theory lightly, practice thoroughly - even without complex background knowledge, we focus on learning only the essential points that appear on the exam, centered around past exam questions.

This is a Python basics course for starters who want to grow as data analysts. - Those who want to do data analysis but don't know Python - Those who want to learn machine learning with Python - Those preparing for the Big Data Analytics Engineer practical exam - Those who want to develop machine learning-based applications with Python

This is a lecture on the National Technical Qualification Big Data Analysis Technician Practical with Python. We hope you all pass!