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.

This is a lecture that provides a brief introduction to the field of computer vision.

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.

Learn virtual environment concepts and setup methods.