First Steps in Physical AI Without Hardware: Building an AI That Recognizes Hand Gestures via a Webcam

Are you feeling stuck on how to apply what you've learned to real-world tasks even after mastering the basics? I will help you complete complex RAG and agent designs using my professional industry know-how.

This course is not about non-developer office workers learning coding itself, but rather an education focused on developing the ability to solve business problems directly using AI agents. Previously, one had to rely on IT departments or outsourced development when problems arose, but we are now in an era where you can design alongside AI and create immediate prototypes to implement task automation. The core competencies required for this are problem definition, establishing solution strategies through AI collaboration, and the ability to build the necessary tools yourself. In particular, by utilizing Codex CLI, existing ChatGPT users can practice agentic coding immediately without additional costs, allowing non-developers to quickly gain practical experience. The curriculum is structured step-by-step, covering everything from understanding changes in the AI agent era to development basics, terminal usage, Codex CLI-based agentic coding, problem structuring, Django web app development, and the creation of actual task automation apps. Learners can secure task automation capabilities by directly building applications applicable to real-world work, such as To-Do lists, checklists, schedule management, meeting minutes, and summarization tools. The entire course is designed as a modular micro-learning system composed of short units, allowing for rapid learning of necessary content and immediate reuse during work.

🔥 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 😎💻

This course is designed for developers, AI enthusiasts, and professionals who want to develop real-world AI applications using LangChain, OpenAI, Hugging Face, and Python. Rather than focusing solely on theory, this course takes a practical, project-oriented approach. Throughout the course, students will directly build a total of 15 high-quality AI applications, including chatbots, CSV analysis tools, resume screening systems, invoice extraction bots, support assistants, marketing tools, and text-to-SQL applications. I created this course to make complex AI concepts easy to understand and to ensure modern LLM development is accessible to everyone. Many learners struggle to understand how tools like LangChain, embeddings, memory systems, vector databases, and AI agents interact in real-world applications. This course guides you step-by-step through clear explanations, hands-on coding sessions, and actual implementation workflows. By the end of the course, students will confidently understand how to design, build, and deploy AI-powered applications using the latest generative AI technologies.

This is a course on building your own stock and cryptocurrency automated trading programs using ChatGPT, even without prior coding knowledge. You will gain both AI development skills and financial investment knowledge through hands-on practice covering the entire process, from data collection to predictive model development, stock recommendation systems, and actual automated trading.

Even without coding experience, you can create a real-world work automation program yourself with Cursor AI. This course is a hands-on project in which you use Python and Cursor AI to automatically collect news comments (Crawling), save them as a CSV file, and analyze public opinion and sentiment, creating a complete project from start to finish. This is not a course where you simply type along with the code. It is designed to let you experience the entire real-world development process, including how to ask Cursor AI effective questions, setting up the development environment, writing automation programs, and troubleshooting errors. By following the course, you will learn step by step—from installing Python and configuring Cursor AI to the basics of work automation, scraping news comments, saving data as a CSV file, performing sentiment analysis, and fixing errors that arise in actual projects. Even if you are new to programming, you will naturally learn how to develop alongside AI, automate repetitive tasks, and build practical skills for using data.

If you only know LangChain, it's just a chatbot; but if you know LangGraph and Multi-Agent patterns, it becomes a service. An active AI instructor will share the know-how to build operational AI Agent workflows from start to finish—going beyond simple prompt calls to handling tools, maintaining memory, and incorporating human-in-the-loop verification—using 17 practice notebooks and 4 multi-agent patterns (Subagents, Handoffs, Router, and Skills).

It is difficult to complete a classification service using only AI API calls. Based on practical experience, I guide you through everything from implementation to deployment.

Learn how to use OpenCV and process images through a practical implementation of business card recognition. OpenCV is briefly explained, and the OpenCV functions required to implement business card recognition are explained in more detail. In other words, rather than a basic course, it provides an essence for the practical application of business card recognition. It also includes a method of utilizing Tesseract and Microsoft's OCR engine. The source code of this lecture is based on Python, but since you will learn the OpenCV classes and functions used and the image recognition and processing technology, it will not be difficult to apply it to Android and iOS based on this. Those who take the course will be provided with lecture slides and actual business card recognition source code. The lecture contents were further improved and verified through three offline seminars in January and February 2017, and the instructor has carefully recorded them again for online use. These are the OpenCV functions used in this lecture. cv2.Canny() cv2.GaussianBlur() cv2.VideoCapture() cv2.adaptiveThreshold() cv2.approxPolyDP() cv2.arcLength() cv2.boundingRect() cv2.boxPoints() cv2.contourArea() cv2.convertScaleAbs() cv2.createTrackbar() cv2.cvtColor() cv2.destroyAllWindows() cv2.dilate() cv2.drawContour s() cv2.findContours() cv2.getAffineTransform() cv2.getPerspectiveTransform() cv2.getTrackbarPos() cv2.imread() cv2.imshow() cv2.imwrite() cv2.minAreaRect() cv2.namedWindow() cv2.rectangle() cv2.resize() cv2.threshold() cv2.waitKey() cv2.warpAffine() cv2.warpPerspective()

When researching AI or conducting a project using it, basic paper implementation is essential. Let's upgrade our practical skills by implementing an actual paper through this lecture!

You can acquire an overview of machine learning and deep learning, how to use basic tools, and the Python language knowledge necessary for learning in a short period of time.

This course covers everything from the basic concepts of recommendation systems to the principles of applying deep learning. Develop your practical skills for recommendation service development by learning various recommendation algorithms, including collaborative filtering, content-based filtering, and hybrid recommendation systems!

This lecture examines the entire process of generating a photo mosaic from an algorithmic perspective. The input image is reduced to a set of representative colors matching the number of tiles through K-means clustering, then the Hungarian algorithm is applied to optimally match each color with a tile in a 1:1 correspondence. Through this, you will understand how image processing and combinatorial optimization algorithms combine to create a single visual output.

Let's create a web app that uploads an image and uses OpenCV to process it and detect faces.

If you want to properly learn OCR technology that's truly used in practice, this one course is all you need! Aiming for over 98% accuracy even with unstructured documents and complex layouts, based on the latest SOTA models and real-world know-how, we build enterprise-level OCR projects together.

When you learn machine learning, you learn how to improve accuracy. But the moment you try to put that model onto an actual chip, questions no one has answered remain. How many multiplications does this model perform? How much does it need to remember, and for how long? Can the chip specifications you are targeting handle those requirements? Machine learning textbooks talk about accuracy, and semiconductor textbooks talk about circuits, but materials that bridge the gap between them are rare. I repeatedly encountered this gap while implementing RISC-V CPUs and NPUs on FPGAs. The model with the highest accuracy often turned out not to fit on the board. In this course, you will build six algorithms directly in Python, measuring the number of multiplications, comparisons, memory usage, and accuracy each time. Then you will convert those figures into the resources of an actual FPGA board. Saying that something requires a certain number of multiplications is not enough to gauge its size, but knowing that it uses a certain percentage of the board makes the decision clearer. After nine Labs, when the six models are brought together in a single table, an unexpected picture emerges. We spent nine lessons counting multiplications, but multiplications were not what held us back. After that, we reduce floating-point values to integers, manage bit widths, and even establish criteria for evaluating the circuit. You do not need an FPGA board. The course is conducted entirely in Python, and the board is used only as a reference for converting the measurements.

We solve the challenge of knowing Python syntax but struggling to build services through hands-on experience at Naver and step-by-step practice.

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.

Solve the point where 80% get stuck at makeathons. Complete Raspberry Pi · Computer Vision · LLM · 3D Design in 4 weeks! Achieve top rankings at makeathons with a demonstrable smart mirror PoC!

This course is not just about "how to implement" a Transformer, but about dissecting why this architecture was created, what role each module plays, and how the entire model works from the designer's perspective. We deeply analyze the internal computation principles of Self-Attention and Multi-Head Attention, and directly verify through formulas, papers, and implementation code what limitations Positional Encoding, Feed-Forward Networks, and Encoder·Decoder structures were introduced to solve. Starting from Attention, we assemble the entire Transformer structure ourselves, and actually perform training to experience firsthand how the model operates. This course is the most structured and practical roadmap for "anyone who wants to completely understand Transformers."