Calculus for AI — Derivatives, Gradients, and How Neural Networks Learn

This is a linear algebra course that explores the meaning of vectors and matrices through illustrations and works through calculations using small examples. It covers the mathematics used in linear regression, PCA, SVD, tensors, and attention step by step. No programming knowledge is required.

In-depth linear algebra for engineering majors in machine learning, AI, robotics, computer vision, and related fields. Recommended for those who want to study linear algebra in depth. The material is explained as simply as possible while covering advanced topics through focused selection of subjects.

DNN, CNN, RNN? A deep learning practical course where you can perfectly organize core deep learning algorithms and actually put them to use, even with professional terminology that may seem difficult!

Putting a neural network on an FPGA — it sounds familiar, but few people have actually done it. If you want to get ahead in capstone projects, competitions, or graduation projects, you need to go beyond training a model: you must be able to build and prove for yourself how its computations actually run inside a chip. This course helps you bridge that gap between theory and physical hardware. From reading the specifications to building a Python golden model, Machine Learning training, Verilog RTL design, and FPGA verification, you will complete a neural network accelerator (NPU) for recognizing MNIST digits written in real people’s handwriting from start to finish. From a Conv layer built with line buffers and parallel MACs, through ReLU, MaxPool, and Flatten, to fully connected layers and Argmax — you will integrate nine blocks into a single chip and prove for yourself that "the Python reference answer and the hardware output do not differ by even one bit (Bit-True)." The course also covers how to overcome that frustrating moment when the simulation runs perfectly, but the results are subtly different. We will walk through practical know-how that general deep learning textbooks do not cover, one step at a time — including integer quantization, array-axis ordering conversions, and preventing accumulator overflow. Drawing on the trial and error I have experienced through extensive work with RISC-V CPU design and FPGA Bit-True verification, I have built those lessons into this course so that you do not have to repeat them. By the end of the course, you will have a complete hardware project in hand and be able to say, "I designed it myself and proved it.&quot

Through a systematic curriculum of 40 lectures, you will learn everything from the basic theories of AI to the applied AI technologies of each algorithm. Through mathematical intuition and R coding algorithm learning and practice, you will develop immediately applicable AI model development capabilities, covering everything from designing algorithm models for data analysis, machine learning, and their application tools to selecting and utilizing them.

This course is a comprehensive program that covers everything you need to know to utilize generative AI in practical work settings, from the basic principles of LLM (Large Language Models) to RAG (Retrieval-Augmented Generation), and even the latest technologies like AI Agent and MCP (Modular Command Protocol). It is structured to naturally teach you how generative AI understands, searches, judges information, and extends into AI Agents that take action, following the flow of technological development.

This is a basic course on machine learning and deep learning analysis for data analysis beginners.

This course delves into complex variables, differential equations, and linear algebra, providing a comprehensive understanding of these essential mathematical concepts. Learners will explore foundational theories and applications that are crucial for advanced studies in mathematics and engineering.

This lecture is designed for job seekers preparing for Evaluation and Analysis roles in Samsung Electronics' DS Division (Memory, S.LSI, Foundry, TSP, AVP) and PE, AE, and Solution PE roles at SK hynix, who are struggling with the differences between business units and job functions. You will learn how to categorize job titles by company based on the actual workflow of Product Evaluation roles and how to translate your major-related experiences into professional terminology suitable for resumes and interviews. We will help you establish an application strategy by connecting experiences in Analog circuit design, Verilog/FPGA, process experiments, and data analysis with key industry terms such as Yield, Wafer Map, Shmoo Plot, and Failure Analysis.

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!

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 everything from the basics to hands-on practice of AI platforms, and is a program where you can learn AI image generation technology. Learners can understand the fundamental concepts of AI and develop the ability to generate AI images using various tools and technologies. Through this course, you can enhance your understanding of the AI field and learn how to directly generate AI images in real-world applications.

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.

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

This course is an introductory program designed so that learners who are new to AI technology can easily understand and follow along. Through the lectures, you will learn the basic concepts and usage methods of AI platforms, and conduct hands-on practice directly generating images using various AI tools. Upon completing this course, you will become much closer to AI and acquire the capability to create AI images that can visually implement creative ideas.

Building a Full-Stack System Without Coding: Complete the entire pipeline from data collection to AI/ML analysis and web dashboards using only Korean prompts (Vibe Coding). Owning a 100% Automated Pipeline: Secure an independent stock analysis tool that sends S&P 500 screening and investment opinions via Telegram every morning. Acquiring a Practical Data-Based Investment Framework: Master institutional-level data analysis and risk management capabilities based on source code currently in actual operation.

- Practical Kaggle Competition Project: From Data Exploration to Submission - Beyond Tutorials: Follow a Real Kaggle Competition from Start to Finish Have you signed up for Kaggle and completed the Titanic tutorial, only to feel lost about where to start when facing a real competition? If you simply copy someone else’s notebook and submit it, you’ll eventually hit the wall of wondering, "Why isn’t my score improving?" In this course, we’ll work through an actual Kaggle competition from start to finish, covering data exploration, validation design, feature engineering, modeling, and submission. Instead of memorizing code, you’ll develop an intuitive understanding of the competition mindset: “What should I try and why, and how can I validate its effectiveness?” [One line about your competition participation, awards, or practical experience]

This course makes it easy to learn the essential mathematical concepts used in games. People who are already proficient in math often take this knowledge for granted, making it difficult for them to teach from a beginner's perspective. This course assumes you have no prior knowledge and explains everything from the viewpoint of a complete beginner or non-major.

You will build Android/iOS apps based on simple machine learning models and learn the fundamentals of machine learning, model conversion using TFLite, and the process of implementing Android and iOS applications.

The AI I trained myself determines stock allocations and places orders on its own. Starting with Python basics and the principles of reinforcement learning, you’ll train your own trading AI using real stock price data. Test it against the market, compare performance, and improve your strategy by adjusting reward functions and training settings. Connect your trained model to Korea Investment & Securities paper trading and automated execution on AWS to build your own automated trading AI—one you can continue to modify and develop even after the course.