Book Image

MATLAB for Machine Learning - Second Edition

By : Giuseppe Ciaburro
Book Image

MATLAB for Machine Learning - Second Edition

By: Giuseppe Ciaburro

Overview of this book

Discover why the MATLAB programming environment is highly favored by researchers and math experts for machine learning with this guide which is designed to enhance your proficiency in both machine learning and deep learning using MATLAB, paving the way for advanced applications. By navigating the versatile machine learning tools in the MATLAB environment, you’ll learn how to seamlessly interact with the workspace. You’ll then move on to data cleansing, data mining, and analyzing various types of data in machine learning, and visualize data values on a graph. As you progress, you’ll explore various classification and regression techniques, skillfully applying them with MATLAB functions. This book teaches you the essentials of neural networks, guiding you through data fitting, pattern recognition, and cluster analysis. You’ll also explore feature selection and extraction techniques for performance improvement through dimensionality reduction. Finally, you’ll leverage MATLAB tools for deep learning and managing convolutional neural networks. By the end of the book, you’ll be able to put it all together by applying major machine learning algorithms in real-world scenarios.
Table of Contents (17 chapters)
Free Chapter
1
Part 1: Getting Started with Matlab
4
Part 2: Understanding Machine Learning Algorithms in MATLAB
9
Part 3: Machine Learning in Practice

Using advanced techniques for model evaluation and selection in MATLAB

Model evaluation and selection are crucial steps in machine learning to ensure the chosen model performs well on unseen data and generalizes effectively. When it comes to advanced techniques for model evaluation and selection in MATLAB, there are several approaches you can consider.

In the subsequent sub-section, we will take a look at the most important techniques for model evaluation and selection.

Understanding k-fold cross-validation

K-fold cross-validation is a widely used technique for model evaluation and selection. It involves partitioning the dataset into k equally sized subsets or folds. The model undergoes training and assessment in k iterations, with each iteration employing a distinct fold as the validation set while using the remaining folds as the training set. The outcomes of each iteration are then averaged to derive a comprehensive performance estimation. This is the essence of how k-fold...