Skip to content

TeamLab/machine_learning_from_scratch_with_python

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Machine Learning from Scratch with Python

λ³Έ κ°•μ˜λŠ” TEAMLABκ³Ό Inflearn이 ν•¨κ»˜ κ΅¬μΆ•ν•œ 데이터 μ‚¬μ΄μ–ΈμŠ€ κ³Όμ •μ˜ 두 번째 κ°•μ˜μΈ λ°‘λ°”λ‹₯ λΆ€ν„° μ‹œμž‘ν•˜λŠ” λ¨Έμ‹ λŸ¬λ‹ μž…λ¬Έ μž…λ‹ˆλ‹€. λ°‘λ°”λ‹₯λΆ€ν„° μ‹œμž‘ν•˜λŠ” λ¨Έμ‹ λŸ¬λ‹ μž…λ¬Έμ€ Part Iκ³Ό Part II둜 κ΅¬μ„±λ˜μ–΄ μžˆμŠ΅λ‹ˆλ‹€.

λ³Έ κ°•μ˜λŠ” TEAMLABκ³Ό Inflearn이 ν•¨κ»˜ μ€€λΉ„ν•œ WADIZ νŽ€λ”©μ˜ 지원을 λ°›μ•„μ œμž‘λ˜μ—ˆμŠ΅λ‹ˆλ‹€. μ•„λž˜ λͺ©λ‘μ— λŒ€ν•œ κ°•μ˜λ₯Ό κ°œλ°œν•  μ˜ˆμ •μž…λ‹ˆλ‹€.

λ˜ν•œ κΈ°μ‘΄ K-MOOC 과정은 μ•„λž˜ λͺ©λ‘μ„ μ°Έκ³ ν•˜μ‹œκΈ° λ°”λžλ‹ˆλ‹€.

Course overview

  • κ°•μ’Œλͺ…: λ°‘λ°”λ‹₯ λΆ€ν„° μ‹œμž‘ν•˜λŠ” λ¨Έμ‹ λŸ¬λ‹ μž…λ¬Έ(Machine Learning from Scratch with Python)
  • κ°•μ˜μžλͺ…: κ°€μ²œλŒ€ν•™κ΅ μ‚°μ—…κ²½μ˜κ³΅ν•™κ³Ό μ΅œμ„±μ²  ꡐ수 ([email protected], Director of TEAMLAB)
  • Facebook: Gachon CS50
  • Email: [email protected]

Course Info

  • λ³Έ 과정은 λ¨Έμ‹ λŸ¬λ‹μ— λŒ€ν•œ κΈ°μ΄ˆκ°œλ…κ³Ό μ£Όμš” μ•Œκ³ λ¦¬μ¦˜λ“€μ— λŒ€ν•΄ μ΄ν•΄ν•˜κ³  κ΅¬ν˜„ν•˜λŠ” 것을 λͺ©μ μœΌλ‘œ 함
  • λ³Έ 과정을 톡해 μˆ˜κ°•μžλŠ” 데이터 κ³Όν•™μ—μ„œ μ‚¬μš©λ˜λŠ” λ‹€μ–‘ν•œ μš©μ–΄μ— λŒ€ν•œ 기본적인 이해λ₯Ό ν•  수 있음
  • λ³Έ κ³Όμ •μ˜ 기본적인 ꡬ성은 μ•Œκ³ λ¦¬μ¦˜μ— λŒ€ν•œ μ„€λͺ…, Numpyλ₯Ό μ‚¬μš©ν•œ κ΅¬ν˜„, Scikit-Learn을 μ‚¬μš©ν•œ νŒ¨ν‚€μ§€ ν™œμš©μœΌλ‘œ 이루어 μ Έ 있음
  • μˆ˜κ°•μžλŠ” λ¨Έμ‹ λŸ¬λ‹μ—μ„œ 주둜 μ‚¬μš©λ˜λŠ” μ•Œκ³ λ¦¬μ¦˜μ„ κ΅¬ν˜„ν•˜κΈ° μœ„ν•΄ 고등학ꡐ μˆ˜μ€€μ˜ 톡계학과 μ„ ν˜•λŒ€μˆ˜ν•™μ˜ 이해가 ν•„μš”ν•¨
  • μˆ˜κ°•μžλŠ” λ³Έ 과정을 톡해 Numpy, Pandas, Matplotlib, Scikit-Learn λ“± 데이터 뢄석을 μœ„ν•œ 기본적인 파이썬 νŒ¨ν‚€μ§€λ₯Ό μ΄ν•΄ν•˜κ²Œλ¨

Course Contents

Chapter 1 - Introduction to Machine Learning

Chapter 2 - Warm Up Section: An understanding of data

Lecture

Supplements - Linear algebra

Chapter 3 - Numpy Section

Lecture

Supplements

Chapter 4 - Pandas Section #1

Lecture

Chapter 5 - Pandas Section #2

Lecture

Chapter 6 - Matplotlib Section & Miniproject

Lecture

Chapter 7 - Linear Regression

Lecture

  • Chapter overview - κ°•μ˜μžλ£Œ, κ°•μ˜μ½”λ“œ, μ½”λ“œλ‹€μš΄λ‘œλ“œ
  • Linear regression overview - κ°•μ˜μ˜μƒ
  • Cost functions - κ°•μ˜μ˜μƒ
  • Normal equation - κ°•μ˜μ˜μƒ
  • Lab Assignment: Normal equation - PDF, κ°•μ˜μžλ£Œ
  • Gradient descent approach - κ°•μ˜μ˜μƒ
  • Linear regression wtih gradient descent - κ°•μ˜μ˜μƒ
  • Linear regression implementation wtih Numpy - κ°•μ˜μ˜μƒ
  • Multivariate linear regression models - κ°•μ˜μ˜μƒ
  • Performance measure for a regression model - κ°•μ˜μ˜μƒ
  • Linear regression implementation wtih scikit-learn - κ°•μ˜μ˜μƒ
  • Lab Assignment: Gradient descent - PDF, κ°•μ˜μžλ£Œ

Chapter 8 - Linear Regression extended

Lecture

  • Chapter overview - κ°•μ˜μžλ£Œ, κ°•μ˜μ½”λ“œ, μ½”λ“œλ‹€μš΄λ‘œλ“œ
  • Stochastic gradient descent - κ°•μ˜μ˜μƒ
  • SGD implementation issues - κ°•μ˜μ˜μƒ
  • Overfitting and regularization overview - κ°•μ˜μ˜μƒ
  • Regularization - L1, L2 - κ°•μ˜μ˜μƒ
  • sklearn Linear Model family - κ°•μ˜μ˜μƒ
  • Polynomial regression - κ°•μ˜μ˜μƒ
  • Sampling method - κ°•μ˜μ˜μƒ
  • Kaggle project : Bike demand - κ°•μ˜μ˜μƒ

Chapter 9 - Logistics Regression

Lecture

  • Chapter overview - κ°•μ˜μ˜μƒ, κ°•μ˜μžλ£Œ, κ°•μ˜μ½”λ“œ
  • Logistic regression overview - κ°•μ˜μ˜μƒ
  • Sigmoid function - κ°•μ˜μ˜μƒ
  • Cost function - κ°•μ˜μ˜μƒ
  • Logistic regression implementation with numpy - κ°•μ˜μ˜μƒ
  • Maximum Likelyhood Estimation - κ°•μ˜μ˜μƒ
  • Logistic regression with scikit-learn - κ°•μ˜μ˜μƒ
  • Confusion matrix - κ°•μ˜μ˜μƒ
  • Performance metrics for classification - κ°•μ˜μ˜μƒ
  • ROC curve & AUC - κ°•μ˜μ˜μƒ

Chapter 10 - Logistics Regression extended

Lecture

  • Chapter overview - κ°•μ˜μžλ£Œ, κ°•μ˜μ½”λ“œ
  • Multiclass Classification overview - κ°•μ˜μ˜μƒ
  • Softmax function #1 - κ°•μ˜μ˜μƒ
  • Softmax function #2 - κ°•μ˜μ˜μƒ
  • Softmax regression with numpy - κ°•μ˜μ˜μƒ
  • Performance metrics for classification - κ°•μ˜μ˜μƒ
  • Multiclass classification with scikit-learn - κ°•μ˜μ˜μƒ

Chapter 11 - Naive Bayesian Classifier

Lecture

  • Chapter overview - κ°•μ˜μ˜μƒ, κ°•μ˜μžλ£Œ, κ°•μ˜μ½”λ“œ
  • Probability overview - κ°•μ˜μ˜μƒ
  • Bayes' theorem - κ°•μ˜μ˜μƒ
  • Single variable bayes classifier - κ°•μ˜μ˜μƒ
  • Navie bayesian Classifier - κ°•μ˜μ˜μƒ
  • NB Classifier Implementation - κ°•μ˜μ˜μƒ
  • Multinomial Naive Bayes - κ°•μ˜μ˜μƒ
  • Gaussian Naive Bayes - κ°•μ˜μ˜μƒ
  • NB classifier with sklearn - κ°•μ˜μ˜μƒ
  • 20news group classifaication - κ°•μ˜μ˜μƒ#1, #2

Supplements

Chapter 12 - Decision Tree

Lecture

  • Chapter overview - κ°•μ˜μ˜μƒ, κ°•μ˜μžλ£Œ, κ°•μ˜μ½”λ“œ
  • Decision tree overview - κ°•μ˜μ˜μƒ
  • The concept of entropy - κ°•μ˜μ˜μƒ
  • The algorithme of growing decision tree - κ°•μ˜μ˜μƒ
  • ID3 & Information gain - κ°•μ˜μ˜μƒ
  • CART & Gini Index - κ°•μ˜μ˜μƒ
  • Tree pruning - κ°•μ˜μ˜μƒ
  • Decision Tree with sklearn - κ°•μ˜μ˜μƒ
  • Handling a continuous attribute - κ°•μ˜μ˜μƒ
  • Decision Tree for Regression - κ°•μ˜μ˜μƒ

Chapter 13 - Ensemble

Lecture

  • Chapter intro - κ°•μ˜μ˜μƒ, κ°•μ˜μžλ£Œ, κ°•μ˜μ½”λ“œ
  • Ensemble model overview - κ°•μ˜μ˜μƒ
  • Voting classifier - κ°•μ˜μ˜μƒ
  • Bagging - κ°•μ˜μ˜μƒ
  • Random Forest - κ°•μ˜μ˜μƒ
  • AdaBoost - κ°•μ˜μ˜μƒ
  • Gradient boosting - κ°•μ˜μ˜μƒ#1, μ˜μƒ#2
  • XGBoost & LightGBM - κ°•μ˜μ˜μƒ
  • Installation guide on Windows - κ°•μ˜μ˜μƒ, κ°•μ˜μžλ£Œ
  • Stacking - κ°•μ˜μ˜μƒ

Chapter 14 - Performance tuning

Lecture

Chapter 14 - Support Vector Model

Lecture

Chapter 15 - Neural Network

Lecture

참고자료

Textbooks

  • Reading materials
  • Supplementary textbooks

Prerequisites - μˆ˜κ°•μ „ 이수 λ˜λŠ” μˆ˜κ°•μ€‘ λ“€μ—ˆμœΌλ©΄ ν•˜λŠ” ꡐ과듀

ν‚€μ›Œλ“œ

λ¨Έμ‹ λŸ¬λ‹, λ¨Έμ‹ λŸ¬λ‹ κ°•μ’Œ, λ¨Έμ‹ λŸ¬λ‹ μž…λ¬Έ, Machine Leaning μž…λ¬Έ, Machione Learning κ°•μ’Œ, λ¨Έμ‹ λŸ¬λ‹ κ°•μ˜, λ¨Έμ‹ λŸ¬λ‹ MOOC, Linear Regression, μ„ ν˜•νšŒκ·€, 앙상블, λ”₯λŸ¬λ‹, λ‰΄λŸ΄λ„·, 파이썬, python, 파이썬 μž…λ¬Έ, 파이썬 κ°•μ’Œ, Python μž…λ¬Έ, 파이썬 κ°•μ’Œ, 파이썬 κ°•μ˜, Python κ°•μ˜, Python MOOC, λ°μ΄ν„°λ§ˆμ΄λ‹, Data mining, κ°€μ²œλŒ€ μ΅œμ„±μ² , μ΅œμ„±μ²  ꡐ수, ν”„λ‘œκ·Έλž˜λ° μž…λ¬Έ, ν”„λ‘œκ·Έλž˜λ° κ°•μ’Œ, μ½”λ”©, μ½”λ”© μž…λ¬Έ, 데이터 κ³Όν•™, 데이터 μ‚¬μ΄μ–ΈμŠ€, Data science

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages