machine-learning-with-R
Machine Learning with R @FASTCAMPUS
Week 1: Mahine Learning Overview
- Introduction to data science
- Data science applications
- Machine learning in data science
- Process of machine learning projects
Week 2: Introduction to R
- Data types in R
- Text data handling
- Conditions and loops in R
- Functions in R
- Graphs in R
Week 3: Association Rule Mining (ARM)
- A Ariori algorithm
- ARM application 1: Market basket analysis
- ARM application 2: Finding visiting patterns in exhibitions
- ARM application 3: Recommendation of education programs
- ARM application 4: Predictive maintanence marine structure
- R Exercise
Week 4: Multiple Linear Regression (MLR)
- Multiple linear regression: ordinary least squares (OLS)
- Evaluating the performance of regression algorithms
- Supervised variable selection
- MLR application: Forecasting box office with SNS data
- R Exercise
Week 5: k-Nearest Neigbhor Learning (k-NN)
- k-NN classification
- k-NN regression
- Evaluating the performance of classification algorithms
- k-NN application: spam filtering (classification) & collaborative filtering-based recommendation (regression)
- R Exercise
Week 6: Decision Tree
- Classification and Regression Tree (CART)
- Recursive partitioning & Pruning
- CART application: Late payment prediction model
- R Exercise
Week 7: Naive Bayes and Logistic Regression
- Naive Bayesian classifier
- Logistic regression
- Logistic regression application: customer response modeling in marketing
- R Exercise
Week 8: Linear Discriminant Analysis and Artificial Neural Network
- Linear discriminant analysis (LDA)
- Artificial neural network (ANN)
- Introduction to deep learning
- Structure of convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN)
- ANN application: Virtual metrology in semiconductor manufacturing
- R Exercise
Week 9: Clustering
- Goals and issues in clustering
- K-Means clustering
- Hierarchical clustering
- Self organlizing map
- R Exercise
Week 10: Ensemble
- Background, motivation, and goals
- Bagging
- Boosting: Adaboost, Gradient boosting
- Random forests
- R Exercise