Session_References - KU-BIG/KUBIG_Wiki GitHub Wiki

KUBIG Session과 관련된 추가 자료 입니다.

Contents

1. Machine Learning
2. Preprocessing
3. Modeling
4. Cross Validation
5. Evaluation
6. Regression
7. Regularized Regression
8. Decision Tree
9. Bagging & Random Forest
10. Boosting
11. NN Intro
12. Training Neural Network
13. Distance K-means
14. Hierarchical Clustering
15. Density based Clustering

---

1. Machine Learning

• Machine Learning material

---

2. Preprocessing

• Preprocessing material

---

3. Modeling

• Modeling material
• Objective vs. Cost vs. Loss vs. Error Function

---

4. Cross Validation

• Cross Validation material
• Validating Time Series Forecasting Model

---

5. Evaluation

• Evaluation material

5.1 Bias-Variance trade off

• Quora : What is the best way to explain the bias variance trade off
• Daniel Saunders : the bias variance trade off
• Wikipedia : Bias variance trade off

Noise vs. Bias vs. Variance

• Mathematical foundation for Noise, Bias and Variance
• Wikipedia : 일반화 오차

5.2 Underfitting vs. Overfitting

• 오버피팅 및 언더피팅 이해 및 극복하기

5.3. Evaluation Metric

5.3.1 Classification

• Wikipedia : Precision and recall

m-estimate, Laplace

• Evaluating Probability Estimates from Decision Trees
• Scikit Learn : plot precision recall

5.3.2 Evaluation of Regression

• SST=SSR+SSE
• Regression error metrics

---

6. Regression

• Regression material

---

7. Regularized Regression

• Regularized Regression material

---

8. Decision Tree

• Decision Tree material

---

9. Bagging & Random Forest

• Bagging & Random Forest material
• Bagging과 Boosting 그리고 Stacking

---

10. Boosting

• Boosting material

Boosting & Overfitting

Bagging Decreases Variance, while Boosting decreases bias

• Why Boosting Doesn't Overfit
• Does ensembling cause overfitting?
• Quora : Why is the boosting algorithm robust to overfitting

Boosting models

• xgboost in R

---

11. NN Intro

• NN Intro material
• Progression Bars in Python

---

12. Training Neural Network

• Training Neural Network material

---

13. Distance K-means

• Distance K-means material

---

14. Hierarchical Clustering

• Hierarchical Clustering material

---

15. Density based Clustering

• Density Based Clustering material

---