Machine Learning with MATLAB
This ebook is a good introductory material for a beginner in the field of Machine Learning and contains the links to several MATLAB examples. It includes the following four subjects:
(1) Introducing Machine Learning
(2) Getting Started with Machine Learning
(3) Applying Unsupervised Learning
Cluster analysis: hard clustering vs soft clustering
Hard clustering algorithms: k-means, k-medoids, hierarchical clustering, self-organizing map
Soft clustering algorithms: fuzzy c-means, Gaussian mixture model
Improving models with dimensionality reduction
dimensionality reduction techniques:
principal component analysis (PCA), factor analysis, nonnegative matrix factorization
(4) Applying Supervised Learning
Supervised learning techniques: classification vs regression
Classification algorithms: logistic regression, k nearest neighbor (k-NN), support vector machine (SVM), neural network, naïve Bayes, discriminant analysis, decision tree, bagged and boosted decision trees
Regression algorithms: linear regression, nonlinear regression, Gaussian process regression model, SVM regression, generalized linear model, regression tree
Model improvement involves feature engineering (feature selection and transformation) and hyperparameter tuning.
Feature selection techniques: stepwise regression, sequential feature selection, regularization, neighborhood component analysis (NCA)
Feature transformation techniques: principal component analysis (PCA), nonnegative matrix factorization, factor analysis
Parameter tuning methods: Bayesian optimization, grid search, gradient-based optimization