강의

멘토링

로드맵

/

Introduction to Machine Learning from Scratch

This lecture is the second lecture of the data science course developed by TEAMLAB and Inflearn, Introduction to Machine Learning from Scratch. Introduction to Machine Learning from Scratch consists of Part I and Part II. This lecture was produced with the support of WADIZ funding prepared by TEAMLAB and Inflearn.

(4.3) 41 reviews

995 learners

  • TeamLab
Machine Learning(ML)

Reviews from Early Learners

1. Course Introduction

This introductory machine learning course is the second in a data science course developed jointly by TEAMLAB and Inflearn, titled "Introduction to Machine Learning from Scratch." "Introduction to Machine Learning from Scratch" consists of Parts I and II. This course was developed with support from WADIZ Funding, a joint project between TEAMLAB and Inflearn. We plan to develop courses on the following topics:

Please also refer to the list below for existing K-MOOC courses.

Learning Objectives Helpful people
This course aims to help students understand and implement the fundamental concepts and key algorithms of machine learning. Through this course, students will gain a basic understanding of various terminology used in data science. Anyone who wants to get started with programming, a beginner who wants to learn data science, someone who wants to build a foundation before starting machine learning, or someone who is preparing for a job in the data science field

2. Course Features

  • The basic structure of this course consists of an explanation of the algorithm, implementation using Numpy, and utilization of the package using Scikit-Learn.
  • Students are expected to have a high school-level understanding of statistics and linear algebra to implement algorithms commonly used in machine learning.
  • Through this course, students will understand basic Python packages for data analysis, including Numpy, Pandas, Matplotlib, and Scikit-Learn.

3. What Machine Learning Can Do

4. References

  • Machine Learning (Couera) by Andrew Ng
  • Deep Learning for Everyone by Sung Kim
  • Deep Learning with C++ by Professor Hong Jeong-mo
  • Machine Learning From Scratch [https://github.com/eriklindernoren/ML-From-Scratch]

Code Assignment Analysis Technical Support: Lablup (www.lablup.com)

Textbooks

Reading materials: Data Science from Scratch (Joel Gruss, 2016)
Python Machine Learning (Sebastian Raschka, 2016)
Hands-On Machine Learning with Scikit-Learn and TensorFlow (Aurélien Géron, 2017, PDF)
Data Mining: Concepts and Techniques (Jiawei Han, Micheline Kamber and Jian Pei , 2011, PDF)
Supplementary textbooks: Data Analysis Using Python Libraries (Wes McKinney, 2013)
Machine Learning in Action (Peter Harrington, 2013)
Introduction to Data Science (Rachel Schutt | Cathy O'Neill, 2014)
Machine Learning in Python (Michael Bowles, 2015)
Introduction to Machine Learning Theory (Etsuji Nakai, 2016)

Prerequisites - Subjects you should have taken before or during the course

Introductory Statistics: The Easiest Statistics in the World (Hiroyuki Kojima, 2009)
The World's Easiest Introduction to Bayesian Statistics (Hiroyuki Kojima, 2017)
Probability and Statistics (Professor Lee Sang-hwa, Hanyang University, 2014)
Reading Materials: Data Science from the Scratch - Ch. 5, Ch. 6, Ch. 7 High school science-level linear algebra (review required for basic concepts of matrices and vectors) Essence of linear algebra (3Blue1Brown, 2017)
Linear Algebra (Khan Academy) (Professor Lee Sang-hwa, Hanyang University, 2013)
- Advance Course Reading Materials - Data Science from the Scratch - Ch. 4 High School Science Level Calculus (understanding of concepts required) Essence of Calculus (3Blue1Brown, 2017)
Introduction to Python for Data Science (TEAMLAB, 2017)
Git Pro Git (Scott Chaconne | Ben Straub, 2016)
Git & Github (TEAMLAB, 2016) Git Lecture (Life Coding, 2014)

5. Instructor Introduction

Choi Seong-cheol (Director of TEAMLAB )

Gam Dong-geun, Kang Nam-gu, Kang Dong-hoon, Kang Min-goo, Kang Seung-hyung, Kang Shin-hyun, Kang Jeong-mo, Kang Cheon-seong, Kyeon Eun-kyung, Ko Sang-gyu, Ko Tae-young, Ko Hyeong-ju, Kwak Byeong-woo, Kwak Jun-gyu, Kwak Hyo-eun, Kwon Ki-woong, Kwon Su-rim, Kwon Jun-ho, Kim Kang-han, Kim Ki-beom, Kim Ki-hyun, Kim Dae-hyun, Kim Dong-soo, Kim Beom-young, Kim Sang-ho, Kim Seok, Kim Seol-hwa, Kim Seong-seon, Kim Young-gon, Kim Young-bok, Kim Wan, Kim Woo-jae, Kim Won-jun, Kim Yu-jun, Kim Jae-hoon, Kim Jong-cheol, Kim Joo-ho, Kim Jun-yeop, Kim Jun-cheol, Kim Jun-tae, Kim Ji-hoon, Kim Jin-young, Kim Tae-il, Kim Tae-hyung, Kim Hyun-soo, Kim Hyun-il, Kim Hyun-pyo, Kim Hyung-soo, Kim Hee-jung, Nam Goong-yeong, No Dong-heun, No Jeong-cheol, No Jin-seon, No Tae-joo, Ryu Jae-guk, Ryu Ji-hwan, Mok Jeong-hwan, Moon Jong-bae, Moon Jin-sol, Moon Jin-won, Park Kyung-hwa, Park Dong-hee, Park Du-gang, Park Min-jun, Park Seon-ho, Park Se-won, Park Soo-yeon, Park Shin-young, Park Jae-ho, Park Je-min, Park Jun-hyeon, Park Jin-tae, Park Chan-jin, Park Cheol-hong, Park Tae-gyun, Park Tae-wook, Park Hye-won, Park Hong-seong, Park Hoon-beom, Park Heung-joo, Bae Yoon-seong, Bae I-hwan, Bae Jin-ui, Baek Gil-ho, Baek Sang-il, Byeong-seop Byun, Seo Ki-yong, Seo Dong-jin, Seo Dong-hwa, Seo Yoon-hee, Seo Jae-won, Seok Min-ho, Seong Jeong-mo, Son Ki-chang, Son Baek-mo, Son Yu-yeon, Son Jeong-hoon, Song Min-gyu, Song Eun-jeong, Song Ji-hoon, Shin Dong-soo, Shin Myeong-seok, Shin Ik-soon, Shin Jae-geun, Shin Jeong-hyeon, Shin Jin-gyu, Shin Heon-seop, Ahn Byeong-hun, Ahn Jung-hee, Yang Je-yeol, Oh Seong-woo, Oh Seung-jae, Ok Jae-woo, Woo Ji-won, Won Seon, Won Ha-ri, Wi Jae-hyeok, Yoo Young-ho, Yoon Byeong-gil, Yoon Seok-chae, Yoon Seok-pil, Yoon Sung-hyun, Yoon Jun-seo, Yoon Jin-hwan, Lee Kyung-rok, Lee Kyung-mi, Lee Kyung-eun, Lee Ki-yong, Lee Dae-gyu, Lee Deok-gi, Lee Don-joong, Lee Min-sun, Lee Sang-yeop, Lee Sung-joo, Lee Sung-han, Lee Sung-hoon, Lee Su-hwan, Lee Seung-gyu, Lee Seung-jun, Lee Shin-ae, Lee Yeon-jun, Lee Young-sook, Lee Young-il, Lee Yong-min, Lee Yu-jeong, Lee Eun-seop, Lee Ja-ho, Lee Jae-jun, Lee Jae-hyun, Lee Jeong-yeon, Lee Jeong-ho, Lee Jong-seok, Lee Joo-woong, Lee Joo-won, Lee Ji-seon, Lee Ji-o, Lee Chang-seop, Lee Hyeong-beom, Im Se-min, Im Won-gyun, Im Jong-tae, Im Ji-hong, Im Chae-hyun, Jang Seok-won, Jang Woo-il, Jang Woo-cheol, Jang Jun-hyeok, Jang Hyun-jeong, Jang Hong-gi, Jeon Gyeong-hwan, Jeon Yong-jin, Jeon Jong-yeol, Jeon Jin-myeong, Jeong Gwang-yoon, Jeong Gwang-ho, Jeong Dae-hwan, Jeong Dong-ryeol, Jeong Dong-min, Jeong Seong-uk, Jeong Su-jeong, Jeong Seung-hyeon, Jeong Yeong-gyo, Jeong Yun-gi, Jeong Chan-mo, Jeong Hyang-won, Jeong Hyeon-cheol, Jo Gwang-je, Jo Min-ha, Jo Su-jeong, Jo Young-man, Jo Yong-jun, Jo Won-seok, Jo Jae-moon, Jo Jung-hyun, Joo Jeong-seok, Jin So-ra, Cha Dong-cheol, Cha Jin-man, Chae Ho-jin, Choi Kyung-min, Choi Woong-sik, Choi In-bo, Choi Jeong-won, Choi Je-ho, Choi Jun-sik, Choi Han-dong, Chu Jeong-ho, Ha Jun-soo, Han Bo-ram, Han Seong-uk, Han Seong-hyeon, Han Hyeong-seop, Hyun Seung-cheol, Hong Mi-na, Hong Sim-hee, Hong Jun-won, Hong Tae-hwan, Hwang Dae-seong, Hwang Ui-yeong, Hwang Ji-yeong, Hyo-ju, eric, Sunghuek Park, Lablup, Shin Jeong-gyu, TeamLab, Choi Soo-kyung, Lee Se-ri

Hello
This is

Curriculum

All

139 lectures ∙ (28hr 20min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

All

41 reviews

4.3

41 reviews

  • 백곰이님의 프로필 이미지
    백곰이

    Reviews 9

    Average Rating 4.7

    4

    15% enrolled

    머신러닝의 기본개념을 빠르게 이해하기 좋은 강좌 - 강의의 초반부는 짜임새 있게 진행되는듯 하다가 후반부에서 대략적으로 설명이 되고, 넘어가는 듯한 느낌이네요, 조금 아쉽습니다. - Machnine Learning from Scratch with Python Part II 강좌는 언제쯤 나오는지도 궁금합니다.

    • sckim님의 프로필 이미지
      sckim

      Reviews 1

      Average Rating 5.0

      5

      100% enrolled

      많이 도움 되는 강의였습니다.

      • shuma1359님의 프로필 이미지
        shuma1359

        Reviews 5

        Average Rating 3.6

        4

        100% enrolled

        좋은 강의였습니다

        • 원종갑님의 프로필 이미지
          원종갑

          Reviews 3

          Average Rating 4.0

          3

          100% enrolled

          수학을 어려워 하는 수강생은 어려운 강의 같습니다. 좀 더 쉬운 프로그램 언어 교육이 되었으면 합니다.

          • 이장수님의 프로필 이미지
            이장수

            Reviews 3

            Average Rating 5.0

            5

            100% enrolled

            내용이 많은 만큼 도움이 큰 과정이네요

            Access is restricted to non-public courses.
            Private Course