강의

멘토링

로드맵

AI Development

/

Deep Learning & Machine Learning

I'll study deep learning without going to graduate school - Basis for deep learning

We help you accurately intuit the concepts of the theories that form the basis of deep learning.

(4.5) 18 reviews

1,298 learners

  • sorryhyun96
이론 중심
딥러닝초보
Deep Learning(DL)
Machine Learning(ML)
Thumbnail

What you will learn!

  • Probability Theory, Mathematical Statistics, and Statistical Testing for Deep Learning

  • Essential Linear Algebra, Mathematical Notation

  • Other optimization theory, non-parametric methods, etc.

"I want to study deep learning without going to graduate school." Basis for deep learning

This course covers the fundamentals that remain relevant even amidst the rapid changes in deep learning. Even those new to deep learning theory will find it intuitive and easy to understand!

The theory that forms the basis of deep learning

Just put in the liquid!

Understanding the underlying theory of deep learning means understanding the concepts necessary to understand deep learning, and can be quickly grasped through abstract yet intuitive explanations.

Below is a screenshot of the final part of Lecture 7, "Conditional or Independence." This course covers essential yet abstract and difficult concepts in deep learning, such as IID , in just 12 minutes + (Probability Chapter) Lecture 1 .

Theory-oriented lectures

The course focuses on theory and does not include practical training. Because the coding environment is rapidly changing, with cloud-based chatGPT Agent coding environments like Dify, Langchain, and NPU-friendly OS, we aim to provide knowledge that will not be outdated by the emergence of new technologies .

Course Curriculum Structure

  • Classical machine learning techniques that are still considered the fundamental principles of deep learning.

  • Uncertainty inference using probability theory

  • An optimization method that combines theoretical approaches from mathematics and heuristics from engineering.

The curriculum was designed around the three contents above.

  1. Concept of statistics-based, linear models

    1. This course covers basic machine learning techniques using statistical techniques and optimization theory.

    2. We deliver only the most important content in linear algebra, optimization, and causal inference in an intuitive manner.

    3. We'll also teach you how to read essential formulas and expressions, helping you progress to more advanced levels.



  2. Probabilistic inference

    1. This lecture will discuss how mathematical statistics and information theory have contributed to machine learning.

    2. We will convey the content as intuitively as possible, including topics that were previously only mentioned in graduate school curricula, such as basic probability theory, mathematical statistics, Bayesian statistics, information theory, and lower risk bound.



  3. Non-linear approaches

    1. This course will cover how complex theories from the 2000s, such as the manifold hypothesis, kernel trick, multi-dimensional probability distribution, and non-parametric methods, relate to deep learning.

    2. We will convey concepts close to the actual operation of deep learning, such as non-linear transformations of space.

This course was created by: Ji Seung-hyun

  • We have been involved in various seminars aimed at conveying intuitive and accurate concepts, with the goal of sharing knowledge through activities such as fake research institutes.

  • He has diverse research and practical experience, including serving as a SIGUL 2024 workshop program committee member, ACL 2023 emergency reviewer, EMNLP 2023 invited reviewer, and publishing history in the Journal of the Korean Information Science Society.

  • For more detailed information, please refer to the notion resume .

Recommended for
these people

Who is this course right for?

  • People who want to understand Deep Learning a little less abstractly

  • Someone recently growing skeptical of ChatGPT, LLMs

  • Those wishing to apply for AI Graduate School

Need to know before starting?

  • TOEIC 700 or higher English proficiency

  • High school humanities level math knowledge

Hello
This is

2,552

Learners

77

Reviews

1

Answers

4.5

Rating

4

Courses

안녕하세요, 바임컨설팅그룹에서 IT 컨설턴트로 일하고 있는 지승현이라고 합니다.

상세한 소개는 다음 링크 참고 바랍니다.

https://inf.run/rzZVT

 

Curriculum

All

17 lectures ∙ (4hr 20min)

Published: 
Last updated: 

Reviews

All

18 reviews

4.5

18 reviews

  • 김현재님의 프로필 이미지
    김현재

    Reviews 1

    Average Rating 5.0

    5

    35% enrolled

    정말 도움이 됩니다. 혼자 찾아볼땐 답이 없이 어려웠는데 가이드라인을 제시해 주시는거 같습니다 감사합니다!

    • 이현종님의 프로필 이미지
      이현종

      Reviews 1

      Average Rating 5.0

      5

      56% enrolled

      • 똘똘이스머프님의 프로필 이미지
        똘똘이스머프

        Reviews 868

        Average Rating 5.0

        5

        100% enrolled

        귀한 강의 감사드립니다. 건강 조심하세요.

        • 지승현
          Instructor

          코로나가 다시 유행이라고 하더라고요 ㅜㅜ 스머프님도 건강하세요~

      • 최지원님의 프로필 이미지
        최지원

        Reviews 2

        Average Rating 5.0

        5

        100% enrolled

        • 쿠카이든님의 프로필 이미지
          쿠카이든

          Reviews 484

          Average Rating 5.0

          5

          18% enrolled

          Free

          sorryhyun96's other courses

          Check out other courses by the instructor!

          Similar courses

          Explore other courses in the same field!