강의

멘토링

로드맵

AI Development

/

Deep Learning & Machine Learning

Deep Learning Next Generation Innovation Technology - Introduction to Physical Information Neural Networks and Pytorch Practice

This is a lecture that studies the physical information neural network, one of the next-generation innovative technologies of deep learning, and implements it directly using Pytorch. Let's learn the next-generation innovative technology of artificial intelligence with me!

(4.9) 14 reviews

166 learners

  • dlbro
3시간 만에 완강할 수 있는 강의 ⏰
딥러닝모델
PyTorch
Deep Learning(DL)
Machine Learning(ML)
Artificial Neural Network

Reviews from Early Learners

What you will learn!

  • The concept of physical information neural network, the next-generation innovative technology in artificial intelligence

  • Building a Physical Information Neural Network Using PyTorch

Emerging next-generation deep learning models
Physical Information Neural Network (PINN)

Deep learning models that integrate the laws of physics are emerging as a new key to AI problem-solving. Jensen Huang, CEO of NVIDIA, emphasized the potential of AI, stating that the next wave of AI will be one that learns about the physical world . Among these models, the most notable is the Physical Information Neural Network (PINN) .



[Google Trends] Soaring Interest in Physics-Informed Neural Networks


Physics-informed neural networks (PNNs) are artificial neural networks built by learning from physical information. Combining the performance of neural networks with the power of physical information, they enable the accurate construction of complex systems even with limited data, and are considered a next-generation innovation in the industrial sector.

NVIDIA , a leader in artificial intelligence (AI) computing, has also launched its AI framework, Modulus, introducing physics-based machine learning models as a groundbreaking technology . Many companies, including NVIDIA, Amazon, Philips, ExxonMobil, SpaceX, BMW, and Siemens, are investing in and developing physics-based neural networks, and expect physics-based machine learning models to drive next-generation innovation across industries.

Why Physical Information Neural Networks?

(1) Solving various challenges

Physical information neural networks, which integrate the laws of physics into deep learning, are solving various challenges previously intractable to deep learning and expanding the range of industries applying deep learning . Recently, they have been adopted in fields such as medicine (new drug development), the environment (climate prediction), and architecture (structural design), attracting attention as an attractive technology.

Nvidia's Modulus

(2) Less data usage

Supervised learning, the fundamental learning method for artificial neural networks, typically requires massive amounts of data. On the other hand, physics-based learning, which makes predictions based on physical laws, can build accurate models without data or with only a small amount of data .

Physical information neural network

(3) Establishing a system that combines transparency and efficiency.

Physical neural networks can be integrated with various technologies to enhance accuracy in various fields and significantly improve computational speed compared to existing methods . Furthermore, because the model's predictions and decision-making processes are based on the laws of physics, they can help address the "black box" problem inherent in deep learning .

FEM vs PINN

From theory to implementation
Contains the basics of physical information neural networks

In this lecture, after learning the concepts, we will implement models for various problems.

To prevent math from becoming a barrier, we cover the concept of differentiation first.
Introduces the concept of physical information neural networks and the learning principles of neural networks.
You can implement a physical information neural network yourself through 6 exercises.


Things to note before taking the course

Practice environment

  • The hands-on training takes place on Google Colaboratory, which requires no separate installation . A free Google account is required, and failure to use Colaboratory may result in disruption to the training.

Learning Materials

  • All slides and code used in the class are provided.

  • Implement the model using Pytorch.

Player Knowledge and Precautions

  • Some basic knowledge of deep learning, such as supervised learning and gradient descent, is required.

  • This course covers a wide range of mathematical topics, including differential equations and numerical analysis. However, it's structured so that even those without prior knowledge of differential calculus can easily follow along.

  • This is a question-based course. Questions about the class are always welcome. :)

Recommended for
these people

Who is this course right for?

  • Those preparing for universities/graduate schools related to artificial intelligence

  • Anyone who wants to follow the future of artificial intelligence

  • Anyone who wants to experience the next-generation deep learning innovation technology

Need to know before starting?

  • Passion to do

  • Deep Learning Basics

  • Basic knowledge of Python

Hello
This is

4,886

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)

 

 

 

 

Curriculum

All

19 lectures ∙ (2hr 22min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

All

14 reviews

4.9

14 reviews

  • 아쿠아라이드님의 프로필 이미지
    아쿠아라이드

    Reviews 12

    Average Rating 5.0

    5

    74% enrolled

    현업에서 PINN 에 대해 키워드를 듣고 매우 궁금해 하던차였지만 관련자료도 많지 않고, 체계적으로 설명한 한국어 강좌는 더더욱이 없었는데, 짧은 시간에 개념을 쉽게 이해할 수 있도록 핵심 콕콕 설명해 주시는 강의를 만났습니다. 만약 좀 더 복잡한 실전 문제를 다루어 주는 advanced 추가 PINN 강의를 개설해 주시면 저는 100% 수강하겠습니다 ㅎㅎ PINN 유투부등을 찾아보아도 기계공학의 학부 시험에 나올만한 단순한 물리 문제에 적용한 사례설명이 대다수이다보니 현업 적용할 수는 없어서요~~ 예를 들면 3차원 CFD 문제라든지 일기예보 이미지 예측, 3D 기계시스템의 충돌 혹은 거동 등의 실전 문제에 적용한 사례를 advanced 강좌에서 code level 에서 풀어주신다면 현업 적용에 도움이 정말 많이 될 것 같습니다. 물론 지금 강의도 강추입니다 ^^

    • 딥러닝호형
      Instructor

      수강평 너무 감사드립니다. 궁금하신거 있으면 언제든 질문 주세요!!

    • 배터리나 수명에 적용하는 advanced 강의 만들어 주시면 안될까요?? 코드 위주 설명이면 좋을것 같습니다.

  • ab님의 프로필 이미지
    ab

    Reviews 1

    Average Rating 5.0

    5

    32% enrolled

    겁내 어려운데 누군가는 이런 설명해주는 게 좋네요. 국내에 이정도 강의가 드물거든요. ㅋㅋ

    • 딥러닝호형
      Instructor

      난이도 조정에 고민이 많았는데 이렇게 극찬해주시니 감사드립니다. 열공 하시고 언제든 질문주세요!

  • 도덕호님의 프로필 이미지
    도덕호

    Reviews 4

    Average Rating 5.0

    5

    100% enrolled

    • 김현우님의 프로필 이미지
      김현우

      Reviews 1

      Average Rating 5.0

      5

      32% enrolled

      • 신경식님의 프로필 이미지
        신경식

        Reviews 2

        Average Rating 5.0

        5

        100% enrolled

        $55.00

        dlbro's other courses

        Check out other courses by the instructor!

        Similar courses

        Explore other courses in the same field!