Shin Kyung-shik's Deep Learning Odyssey - Introduction to Computer Vision

This is a lecture that condenses the mathematics curriculum taught in middle and high school. You will learn the necessary mathematical knowledge and techniques through extensive practice for each item.

Learn virtual environment concepts and setup methods.

We will summarize the theoretical concepts of MNIST, the most fundamental dataset in computer vision, and learn how to implement it using Torchvision's API as well as how to implement a custom dataset class directly.

This course provides a complete theoretical overview of the operations of convolutional and pooling layers, which are the core modules of Convolutional Neural Networks, and helps you develop implementation skills by building them yourself.

This lecture focuses on convolution, the most important operation in computer vision using deep learning.

Build a solid theoretical foundation of images essential before learning deep learning-based computer vision. Understand the essence of image data, such as pixels, resolution, and color representation, and cultivate practical programming skills to read, transform, and preprocess images using Python.

This is a lecture on implementing practical code using PyTorch features based on the code directly implemented in Gradient-based Linear Regression (1). Additionally, it's a lecture where you'll theoretically learn about the necessity of data preprocessing, its theory, and its impact on learning, and implement it with practical code.

This is a lecture for perfectly understanding the process of training the simplest form of deep learning model using gradient descent.

This is a course that intensively covers gradient descent, the most fundamental learning algorithm in deep learning.

This is a course where you learn the basic calculus and PyTorch's Autograd functionality needed to get started with deep learning.

This is a lecture on data visualization using the Matplotlib library.

This is a lecture on how to use NumPy and practice its application in real-world scenarios.

This is the fifth lecture in the [인공지능을 위한 파이썬] series. It is a course that provides practical exercises used in Machine Learning and Deep Learning, along with Python grammar.

[Python for AI] This is the fourth lecture in the series. It is a lecture that covers Python grammar along with practical exercises used in machine learning and deep learning.

[Python for AI] Third lecture in the series. Learn how to debug Python code.

This is the second lecture in the [Python for AI] series. It's a lecture that provides practical exercises used in machine learning and deep learning, alongside Python grammar.

This is a course that offers extensive practice in Python's basic syntax. This is a course that provides practical exercises used in Machine Learning and Deep Learning, along with Python's syntax.

This is the first lecture in linear algebra, and it is a lecture that geometrically understands vectors and vector operations.

Limits of functions, derivatives, differentiation rules, derivative formulas, applications of differentiation

This course teaches you how to use LaTeX to write formulas.

We will summarize the theoretical concepts of MNIST, the most fundamental dataset in computer vision, and learn how to implement it using Torchvision's API as well as how to implement a custom dataset class directly.

Build a solid theoretical foundation of images essential before learning deep learning-based computer vision. Understand the essence of image data, such as pixels, resolution, and color representation, and cultivate practical programming skills to read, transform, and preprocess images using Python.

The automotive and parts manufacturing industry is a field where innovation is essential amid fierce global competition and complex supply chains. This course focuses on how AI technology can be applied in the field, explaining actual cases including production efficiency improvement, quality inspection automation, equipment predictive maintenance, and supply chain optimization. From the foundational understanding needed for AI implementation to strategies and risk management considerations for field application, this course covers topics step by step, providing knowledge and insights that practitioners and managers can immediately utilize.

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 course is a hands-on program for practicing the fundamentals of machine learning mathematics and statistics using Python. While machine learning and deep learning require programming skills, a mathematical background is necessary to understand the underlying principles. Through this course, you can step-by-step master the foundational mathematics required for artificial intelligence.

You can create a deep learning analysis environment in the cloud using Docker. When Docker images managed by Google, MS, etc. are combined with the cloud, you can work with the latest deep learning analysis methods on your computer.

Let's implement a deep learning framework directly with Excel! Let's solve supervised learning/unsupervised learning/reinforcement learning with the implemented framework!

Do you want to become a data analytics expert of the future? Grab your chance now! This is a unique opportunity to explore infinite possibilities and learn how to derive powerful insights through cutting-edge artificial intelligence technology and big data.

Build your own powerful stock price analysis model that analyzes over 40 types of economic indicators and stock price data using AI to predict not only the S&P 500 and QQQ ETFs but also individual stocks!

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 :)

🚀 Practical AI Anomaly Detection with Databricks! 💡 Stop using expensive and slow models! From large-scale data optimization to real-time deployment, complete an anomaly detection AI that can be used immediately in corporate practice.

Have you been getting stuck on linear algebra formulas every time you try to study AI? Instead of memorizing formulas, this lecture shows you visually how vectors and matrices actually move in space. By the end of the course, you will be able to interpret the mathematics behind neural networks, PCA, and SVD on your own.

The electronics and semiconductor industry is a field where data-driven management and innovation are particularly crucial due to ultra-precision processes and complex supply chains. This course covers practical strategies that can be directly applied in electronics and semiconductor manufacturing, including defect detection, process optimization, predictive maintenance, and supply chain management using AI technology. Along with real-world cases from global companies, the course also presents low-cost, high-efficiency AI implementation methods that small and medium-sized enterprises can realistically utilize. Through this, students will be able to understand and apply AI-based manufacturing strategies that not only improve productivity and reduce costs, but also build future competitiveness.

This course explains the basic concepts of LLM and GPT in an easy-to-understand way for everyone. Students will build their own chatbot using the GPT API and deploy it on the web using Streamlit. By experiencing everything from the basics to hands-on practice, you can build a solid foundation for your first steps in utilizing AI.

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.

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.

See exam types and trends at a glance! Strengthen your practical skills with approximately 100 questions. The perfect preparation for the AWS AI Practitioner exam, allowing for systematic study even when preparing on your own.

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.

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.

From Multi-Head Attention to the Original Transformer model, BERT, the Encoder-Decoder based MarianMT translation model, and even Vision Transformer, you'll learn Transformer inside and out by implementing them directly in code.