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

Discovering DL architectures

DL models are essentially multi-layered NNs, which refers to NNs that comprise multiple hidden layers (at least two) structured hierarchically. This hierarchical arrangement facilitates the sharing and reuse of information. Across this hierarchy, one can pinpoint features while disregarding unnecessary intricacies, thereby enhancing invariance. Within the realm of multi-level ML, deeper tiers acquire inputs from the outputs of prior layers and execute more complex transformations and abstractions. This layering approach to learning draws inspiration from the information processing and learning methods of mammalian brains, enabling them to react to external stimuli.

DL architectures are the fundamental blueprints that underlie the construction of DNNs, enabling them to effectively learn and represent complex patterns and features from data. These architectures define the layout, connections, and flow of information within the network, determining how...