Machine and Deep Learning Using MATLAB: Algorithms and Tools for Scientists and Engineers

Machine and Deep Learning Using MATLAB is a comprehensive resource that covers machine and deep learning methods using MATLAB tools and algorithms. It provides insights and algorithmic decision-making processes for exploring machine and deep learning applications, with a focus on numeric data acquisition, analysis, image acquisition, and analysis, and retraining and creation for image labeling, object identification, regression classification, and text recognition.

Format: Hardback
Length: 592 pages
Publication date: 16 October 2023
Publisher: John Wiley & Sons Inc

Machine and Deep Learning Using MATLAB is a comprehensive resource that delves into the realm of machine and deep learning methodologies utilizing MATLAB tools and algorithms. It provides insights and algorithmic decision-making processes for early career professionals seeking to harness the power of MATLAB for exploring machine and deep learning applications.

The book begins by introducing the relevant MATLAB tool or app and explaining its usage for a specific method or a collection of methods. It outlines the properties of the tool, including its input and output arguments, and highlights any limitations or applicability through accompanying text or tables. A comprehensive running example is presented, showcasing all the necessary MATLAB command prompt code.

In addition to providing MATLAB code, the text also presents the results, typically in the form of figures or tables, alongside the corresponding MATLAB code. This allows readers to follow along and replicate the results for their own purposes. The MATLAB written code can be later used as a template for solving new cases or datasets.

Throughout the text, practical examples are included in each chapter for self-study. An accompanying website offers solutions and coding samples to reinforce the learning experience. Highlighted notes draw attention to critical points or issues, enhancing the reader's understanding.

Furthermore, the book covers various topics related to machine and deep learning, including:

Numeric Data Acquisition and Analysis: Applying computational algorithms to predict numeric data patterns, such as clustering or unsupervised learning.

Relationships between Predictors and Response Variable: Exploring supervised learning, which involves categorically subdividing into classification (discrete response) and regression (continuous response).

Image Acquisition and Analysis: Employing neural networks for image acquisition and analysis, including estimating net accuracy, net loss, and RMSE for successive training, validation, and testing steps.

Retraining and Creation for Image Labeling, Object Identification, Regression Classification, and Text: Discussing the processes of retraining and creating models for image labeling, object identification, regression classification, and text.

By utilizing the comprehensive coverage provided in Machine and Deep Learning Using MATLAB, early career professionals can gain a solid foundation in machine and deep learning techniques using MATLAB tools and algorithms. The book equips readers with the knowledge and skills necessary to apply these methodologies to real-world problems and make informed decisions based on data analysis.

Weight: 1256g
Dimension: 185 x 263 x 40 (mm)
ISBN-13: 9781394209088