[PyTorch] 実戦人工知能へとつながるディープラーニング - 基礎から論文実装まで
dlbro
AI分野で活用度が非常に高いディープラーニングフレームワークであるPytorchを利用して、様々な人工神経網を実装する講義です。
초급
Deep Learning(DL), Python, PyTorch
This is a lecture that studies Vision Transformer, one of the latest deep learning technologies, and implements a paper using Pytorch. Come experience the new future of the vision field with me!
1,129 learners
Pytorch Intermediate Level
Tesla Autonomous Driving and Transformer Concept Based on ChatGPT
A New Paradigm in Image Processing - Vision Transformer
The latest vision transformer, from basics to thesis implementation!
One of the latest trends in image processing is the Vision Transformer . Less than a year after its introduction, improved models have emerged, and even Tesla, a leader in autonomous vehicle development, is building models that combine CNNs and Transformers.
The first half of the lecture explores the current state of the image field, starting with Tesla's story. The second half delves into the concepts of attention and transformers, which form the foundation of vision transformers. The second half delves into the theory of vision transformers and their practical implementation using PyTorch .
A thorough understanding is essential for implementation, allowing you to better understand existing issues. This course will help you understand the concepts and implement them together!
We provide lecture materials.
Q. Can non-majors also take the course?
Basic understanding of deep learning concepts and experience with PyTorch are required. Studying the following subjects first will greatly enhance your understanding.
Q. Can I understand the latest deep learning technologies with just the basics?
You can certainly do it. This class is designed for those with basic knowledge, and the explanations are very detailed.
Q. What program do you use?
All exercises (Python/PyTorch) are conducted on Google Colab, which requires no separate installation . A free Google account is required, and failure to use Colab may result in disruption to the exercises .
Q. Are there any special advantages to this course?
It's true that models based on convolutional neural networks (CNNs) continue to evolve. However, research into implementing models without convolutions has continued, and results are now surpassing those based on CNNs . This lecture, the first of its kind in Korea, covers both theory and implementation, allowing you to delve into this new image processing paradigm in detail!
( Deep learning paradigm prediction hit the mark ! This is the first domestic vision transformer concept and implementation lecture. As of 2023, the Transformer series models are overwhelmingly used ! ChatGPT, a hot topic these days, also adopts the Transformer structure.)
Who is this course right for?
Anyone who wants to learn the latest deep learning technology
Anyone who wants to further improve their PyTorch skills
Anyone who wants to know about the overall direction in the field of vision
Those preparing for graduate school related to artificial intelligence
Need to know before starting?
Basic knowledge of Python/PyTorch
Deep Learning Basics
4,879
Learners
337
Reviews
261
Answers
4.7
Rating
7
Courses
안녕하세요.
딥러닝/머신러닝 관련 유튜브를 운영하는 딥러닝 호형입니다.
수학/데이터 분석을 전공하고 다수의 딥러닝 프로젝트를 완료하고 수행하고 있습니다.
머신러닝, 고급 머신러닝, 딥러닝, 최적화 이론, 강화 학습 등의 인공지능 내용과 선형 대수학, 미적분, 확률과 통계, 해석학, 수치해석 등의 수학 내용까지 여러분들과 공유할 수 있는 지식을 가지고 있습니다.
모두 만나서 반갑습니다!
* 관련 이력
현) SCI(E) 논문, 국제 학회 발표 다수
현) 인공지능 관련 대학교 자문 다수
전) K기업 전임 연구원 - 데이터 분석 및 시뮬레이션: 신제품 개발, 성능 향상, 신기술 적용
"딥러닝을 위한 파이토치 입문" 저서 (세종도서 학술부문 2022 우수도서로 선정)
All
13 lectures ∙ (3hr 10min)
Course Materials:
All
85 reviews
4.8
85 reviews
Reviews 2
∙
Average Rating 5.0
5
Vision Transformer(ViT)の基本的な概念と原理、そしてソース実装まで抜ける内容がない良い講義です。 ViTに入門したい方におすすめです。
受講評 ありがとうございます。熱攻してください!
Reviews 4
∙
Average Rating 5.0
Reviews 1
∙
Average Rating 4.0
Reviews 1
∙
Average Rating 5.0
Limited time deal ends in 7 days
$7,616.00
25%
$66.00
Check out other courses by the instructor!
Explore other courses in the same field!