From Introduction to Reinforcement Learning to Deep Q-learning/Policy Gradient

This course will help you build a solid foundation in the basic concepts of reinforcement learning through essential theoretical learning on deep reinforcement learning, and learn the principles of deep reinforcement learning in detail through hands-on practice of implementing actual code using TensorFlow.

AI that thinks and adapts? Now you can build it yourself. Master the core of reinforcement learning with intuitive explanations and code, not complex theories, and grow into a 'practical developer' through finance and industry projects.

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.

Through this course, you will learn and use various functions of machine learning agents, such as multi-agents, curriculum learning, and distributed learning. You will also learn about reinforcement learning algorithms that can respond to curiosity-based exploration and variable inputs.

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.

Through this course, students will learn various reinforcement learning theories and implement them themselves, as well as create a reinforcement learning environment to test the reinforcement learning algorithm implemented using Unity Machine Learning Agents.

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.

Make your own AI autonomous vehicle! This is a course where you can learn about AI and reinforcement learning in the most fun and fastest way. This course was produced by the developer ranked #1 in DeepRacer Korea.

For those who have tried running hand-recognition examples but feel lost when it comes to teaching an AI your own hand gestures and turning them into something useful, I’ll guide you all the way from installation to data collection, training, and completing the web interface using just a webcam, drawing on my experience overseeing development and training vocational instructors.

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.

If you ask an AI to "build a model with this data," the first few lines might look plausible, but as soon as things get slightly complex, it starts using the wrong columns, introduces data leakage, and results in a model that performs worse despite a higher score. This course does not teach you better prompts. Instead, it covers how to directly design a loop (harness) where an agent understands data, plans, writes code, validates its own results, and backtracks when wrong. After manually walking through the five-piece loop of DS-STAR, you will assemble components one by one, from data profile cards, hooks, and skill hierarchies to independent validators and ablation.

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.

Understand the basic concepts and latest trends of big data, and through technical understanding of big data analysis techniques, extract data patterns to present methods for business application. Through big data, you can create new businesses and develop insights into future business environments.

This course aims to cover the latest Gemini API SDK (@google/genai) in a Node.js and TypeScript environment. You will learn how to use multimodal technology to process text, images, and video simultaneously. We will practice the entire process, from issuing an API key to project setup and model calling.

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

From the basics of machine learning & deep learning! Creating and utilizing classification/regression/clustering/artificial neural networks with Python

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 :)

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.

Do you want to automate repetitive tasks with AI without using paid tools? I will share the practical know-how I gained from building systems myself using n8n and Llama. This is not a lecture where you simply learn "how to connect nodes." We will build actual workflows that you can use immediately, such as automatic Google Sheets organization, YouTube subtitle collection, AI fact-checking, and schedule management.

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.