This is a lecture that explains the concepts and fundamentals of Transformers very well. However, there were some chapters where the instructor's voice was a bit difficult to hear, so I had to make sure to turn on subtitles while taking the class, which was a bit disappointing. Nevertheless, it was a lecture at a much higher level than other YouTube videos or online video lectures available on the web. Thank you.

raymid

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."

sotaaz

[Complete NLP Mastery II] Dissecting the Transformer Architecture: From Attention Expansion to Full Model Assembly and Training

Thank you! It seems there were some audio-related issues while updating several sessions. I'll check and fix the parts you mentioned right away.
Thank you so much for your valuable review :)

transformer

self-attention

pytorch

자연어처리(Natural Language Processing)

Sotaaz

입문

초급

중급이상

파이썬

Python

파이토치

PyTorch

Course Introduction

Understanding Core Concepts of Transformers

Implementing Core Transformer Modules

Transformer Full Assembly & Training

Practical Application & Development Direction