Modern Natural Language Processing: From Understanding the Transformer Architecture to Practical LLM Fine-Tuning

You can enhance your development capabilities by deeply exploring the fundamental principles of large language models like ChatGPT and Claude. You will be able to learn a variety of information and development techniques that are not commonly encountered.

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.

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 :)

The era of AI simply providing answers is over. Now is the age of LLM Agents that make decisions and take actions on their own. This course is an introductory lecture where you learn the core principles and structure of agents by implementing them yourself in just 90 minutes of hands-on practice. With minimal complex theory and a code-focused practical flow, you can directly experience "how AI makes decisions and uses tools." Beyond prompt engineering, let's take the first step into AI automation together.

Learn the core principles and practical implementation of Classic RAG, Graph RAG, and Agentic RAG. Design a dynamic routing system that optimizes token efficiency and latency, and build a long-term memory system that combines GraphRAG’s relational network reasoning with Agentic RAG’s self-evaluation loop. This course develops advanced RAG architecture design skills that can be applied directly in real-world settings.

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

In the midst of daily overwhelming tasks and endless repetitive work, you've probably wondered, "Isn't there a smarter and more efficient way to do this?" Haven't you felt frustrated wasting time on drafting reports, repeatedly failing to find new insights in brainstorming meetings, and struggling to keep up with competitors' pace? Right now, the most powerful tool to solve those concerns has emerged. It's Generative AI. This isn't just a trending technology. It's the most fundamental productivity revolution of our time, and those who first capture and utilize this change will become the winners of future business. This course will teach you how to immediately apply Generative AI, which will become your most capable assistant on your desk, to your actual work. Let's set aside complex theories for now. We focus on **"So what can I do with this technology starting tomorrow?"** 💡 We'll help you reclaim your time and creativity. Our core goal is your **'work automation'** and **'creativity maximization'**. 90% reduction in report writing time: Learn how to delegate the creation of reports, proposals, and email drafts that consume your precious time every week to AI. Simply input key data and direction, and AI will immediately complete professional documents for you. You can now focus on being a strategic thinker and leader, not a document writer. Ideas that outpace competitors: Need new marketing campaigns, innovative product designs, or content ideas that captivate customers? Practice using AI as a partner to instantly generate dozens of creative alternatives and predict market reactions. Data-driven smart decision making: Don't get lost in countless materials. AI quickly summarizes vast amounts of data and provides key insights, helping you make strategic judgments based on data rather than intuition. 🛠️ 'Prompts' are the new language. Utilizing Generative AI well ultimately means being good at **'prompt engineering'**. Like commanding a capable employee, the skill of giving clear and specific instructions to AI determines success or failure. In this course, we'll teach you the core formula for **"how to ask questions to get the desired results."** You'll directly write customized prompts optimized for your role - whether you're a marketer, developer, or planner - and experience how dramatically different the results can be. This knowledge will become a core future competency that won't waver no matter what new AI tools emerge. 🏆 Through this course, you'll become a 'future businessman'. Generative AI is no longer a 'choice' but a 'necessity'. If you reject this technology, your competitors will work 10 times faster every day. But if you seize this opportunity, you can be reborn as a 'future-ready talent' who maximizes productivity, leads creative innovation, and dramatically boosts business performance. Don't fear Generative AI. What matters is knowing how to utilize it well. Start your work innovation journey through this course. It will be the one decision that explodes your business potential. Register right now and experience a new way of working where you work less and achieve more.

Find your way through the sea of data and explore the future of artificial intelligence. This course explores the two massive technological trends of Big Data and Artificial Intelligence (AI), examining how they are bringing innovation to our lives and work.

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

This course is for those who are familiar with deep learning terminology but feel overwhelmed by how models learn. Across 13 lectures, it connects and explains the key principles, from the fundamentals of linear models and neural networks to backpropagation, optimization, CNNs, RNNs, and transformers. You will build a solid foundation for studying deep learning systematically by understanding model architectures, the learning process, and the factors that affect performance.

Through this lecture, you'll be able to learn about the AI graduate school admission process and preparation methods from start to finish! I'll also share some great tips to increase your chances of getting accepted!

Time is constantly flowing, and data is constantly accumulating. In this dynamic world, time series data plays a vital role in every aspect of our lives. From the volatility of financial markets to subtle signals of climate change, time series data captures it all. Now learn how to interpret and leverage this powerful data using the power of Python and deep learning!

I would like to introduce the history of AI and the perspective from which we should view the future of AI.

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.

An introductory AI lecture tailored for those new to artificial intelligence! It easily summarizes core concepts from data to generative AI. The goal is not to build AI, but to achieve a level of practical understanding where you can ask the right questions and explain the technology.

The Master Guide to AI for Java Developers! This course shatters the prejudice that AI is the exclusive domain of Python and empowers your Java applications with AI-driven eyes, ears, voice, and even coding capabilities. Grow into an AI Architect based on the OpenAI API. You will directly develop various AI experts such as an AI writer, translator, artist, and coding companion. You will also build a multi-functional AI assistant that integrates core features including text summarization, sentiment analysis, image description, Java code generation, speech-to-text/text-to-speech conversion, and image/subtitle generation. This is a golden opportunity to maximize the competitiveness of existing Java systems by learning how to assign AI roles through system messages and even implement harmful content moderation.

No Coding Skills Required: Build Your Very First Service with Google Stitch An All-in-One AI Development Workflow That Seamlessly Connects Every Step from Planning to Deployment

We provide guidance on what to study for those starting AI development.

We provide an easy understanding of the concepts and principles of generative AI from a humanities perspective, including literature, film, music, and history, while exploring the cultural impacts and life changes AI will bring. We offer practical insights and strategies on how individuals and companies should respond and prepare for the AI era.

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.