Machine Learning
Preface
Introduction
Explanation & Prediction
Terminology
Supervised vs. Unsupervised
Tools you already have
The Standard Linear Model
Logistic Regression
Expansions of Those Tools
Concepts
Loss Functions
Continuous Outcomes
Categorical Outcomes
Regularization
R Example
Bias-Variance Tradeoff
Bias & Variance
The Tradeoff
Diagnosing Bias-Variance Issues
&
Possible Solutions
Bias-Variance Summary
Cross-Validation
Adding Another Validation Set
K-fold Cross-Validation
Bootstrap
Other Stuff
Opening the Black Box
Process Overview
Data Preparation
Model Selection
Model Assessment
The Dataset
R Implementation
Feature Selection & The Data Partition
Regularized Regression
Strengths & Weaknesses
Final Thoughts
\(k\)
-nearest Neighbors
Strengths & Weaknesses
Final Thoughts
Neural Networks
Strengths & Weaknesses
Final Thoughts
Trees & Forests
Understanding the Results
Strengths & Weaknesses
Final Thoughts
Support Vector Machines
Strengths & Weaknesses
Final Thoughts
Wrap-up
Unsupervised Learning
Clustering
Latent Variable Models
Graphical Structure
Imputation
Ensembles
Bagging
Boosting
Stacking
Deep Learning
Feature Selection & Importance
Natural Language Processing/Text Analysis
Bayesian Approaches
More Stuff
Summary
Cautionary Notes
Some Guidelines
Conclusion
Appendix
Bias Variance Demo
Programming Languages
R
Python
Other
Local Interpretable Model-agnostic Explanations
Various Variable Importance Measures
Brief Glossary of Common Terms
References
Machine Learning
Machine Learning
Michael Clark
https://m-clark.github.io/
2019-03-25
