1, Good Articles

2, Note on Machine Learning Andrew Ng Coursera

3, Notes-on-Data-Science-and-Statistic-Learning

This repository is to backup my learning notes.

Statistics

• Point Estimators and Confidence Intervals pdf

Machine Learning

Support Vector Machine with Dual Lagrangian Explained notes slides

• Maximal margin classifier
• Lagrangian Duality
• See more details in Andrew Ng's notes

Neural Networks (Logistic Regression reviewed) notes slides

• Review on Logistic Regression (Maximum log conditional likelihood)
• A summary of popular Activation functions
• Training neural networks
• Classification performance measures: Mis-classification error, Confusion Matrix, Precision, Recall, F1 score
• Common Nueral Network structures: CNN, RNN, GAN, Auto-encoder

Feature Selection (Information Theoretic Metrics and Regularization)notes slides

• Entropy: quantify the uncertainty
• An feature selection algorithm using Mutual information
• Ridge and Lasso regularization, Elastic Net
• Forward, Backward and Mixed selection

Boosting notes slides

• AdaBoosting classifier: algorithms, exponetial loss, parameter updates

Decision Tree and Random Forest notes slides

• Decision Tree growing and pruning, Error Measures (misclassification errer, Gini index, Cross-entropy)
• Random Forest, Bagging, Bootstrap, OOB (out-of-bag) error
• Boosting trees

Linear Algebra

• Possible case of a linear system pdf

Python, Git and Latex pdf

• Include common commands that I often use.