MATLAB Machine Learning Recipes

A Problem-Solution Approach
Fourth Auflage
ISBN: 979-8-8688-2514-9
Verlag: APRESS L.P.

Buch, Englisch, Format (B × H): 178 mm x 254 mm

Harness the power of MATLAB to resolve a wide range of the latest machine learning challenges. The enhanced Fourth Edition is updated with new chapters on advanced machine learning techniques and real-world engineering applications.

This book offers broad appeal for anyone interested in machine learning, with a new introductory chapter on MATLAB for greater accessibility and a dedicated toolbox chapter to streamline modern workflows. It also demonstrates how MATLAB and machine learning can address challenges across various technical fields. New chapters cover key machine learning areas like pattern recognition, system identification, and computer vision, along with application-focused content on advanced engineering topics such as FPGA deployment, space missions, power electronics, and dynamic modeling.

Each example in the book addresses a real-world problem, with fully executable code provided for every solution. You can quickly find and follow step-by-step guidance for specific challenges, enabling you to leverage these technologies to build sophisticated applications in areas such as pattern recognition, autonomous driving, expert systems, and more.

What You Will Learn

• Write code for machine learning, adaptive control, and estimation using MATLAB
• Use MATLAB graphics and visualization tools for machine learning
• Gain knowledge of Kalman Filters
• Build neural networks, including physics-informed models
• Perform system identification and build expert systems
• Work with computer vision and autonomous systems
• Integrate neural networks to FPGA hardware
• Apply machine learning to remaining useful life prediction

Who This Book Is For

Software engineers, control engineers, university faculty, undergraduate and graduate students, hobbyists.

Zielgruppe

Professional/practitioner

Autoren/Hrsg.

Mohsen, Layla

Paluszek, Michael

Thomas, Stephanie

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Business Application Mathematische & Statistische Software

Inhaltsverzeichnis

Part I Using MATLAB.- Chapter 1 Basics.- Chapter 2 Toolboxes for Machine Learning.- Chapter 3 Data for Machine Learning in MATLAB.- Chapter 4 MATLAB Graphics.- Part II Type of Machine Learning.- Chapter 5 Overview.- Chapter 6 Kalman Filters.- Chapter 7 Adaptive Control.- Chapter 8 Fuzzy Logic.- Chapter 9 Simple Neural Nets.- Chapter 10 Classification with Neural Nets.- Chapter 11 Neural Nets with Deep Learning.- Chapter 12 Physics Informed Deep Neural Networks.- Chapter 13 Multiple Hypothesis Testing.- Chapter 14 System Identification.- Chapter 15 Computer Vision.- Part III Applications.- Chapter 16 Autonomous Driving with MHT.- Chapter 17 Spacecraft Attitude Determination.- Chapter 18 Neural networks on FPGAs.- Chapter 19 Position Determination for Landing.- Chapter 20 Remaining Useful Life.- Chapter 21 Neural Aircraft Control.- Chapter 22 Blocks World.- Appendices A A Brief History of Machine Learning.- Appendices B Software for Machine Learning.

Über Autor(innen)

Michael Paluszek is President of Princeton Satellite Systems, Inc. (PSS), which he founded in 1992 to provide aerospace consulting services. He developed the control system and simulations for the Indostar-1 satellite using MATLAB, leading to PSS’s first commercial MATLAB product, the Spacecraft Control Toolbox, in 1995. Since then, he has created toolboxes and software for aircraft, submarines, robotics, and nuclear fusion propulsion, expanding PSS’s product line. He leads the development of hypersonic aircraft, lunar landers, and deep space vehicles.

Previously, at GE Astro Space, he designed and led control systems for missions including GPS IIR, Inmarsat-3, Mars Observer, and the DMSP meteorological satellites, and participated in more than twelve satellite launches, including the GSTAR III recovery. At Draper Laboratory, he worked on navigation and control systems for the Space Shuttle, Space Station, and submarines. Michael holds a bachelor’s in Electrical Engineering and master’s and engineer’s degrees in Aeronautics and Astronautics from MIT. He holds over a dozen U.S. patents and has authored numerous papers and books, including MATLAB Recipes, MATLAB Machine Learning, Practical MATLAB Deep Learning, and ADCS: Spacecraft Attitude Determination and Control Systems.

Layla Mohsen is a software developer at PSS, specializing in machine learning and embedded systems. She holds a bachelor’s degree in Computer Science from the American University in Cairo, where she graduated with highest honors. She was recognized among the top 10% of academic achievers in the School of Sciences and Engineering and received both the Academic Honor Award and a Certificate of Recognition for Research and Creativity. Layla designs and simulates a variety of aerospace and fusion energy systems. Her technical work at PSS includes predictive modeling for estimating the remaining useful life of power electronics for fusion plasma heating, optimizing computational time for particle-in-cell simulations, computational fluid dynamics of hypersonic inlets, and simulating a multi-stage induction coilgun system in MATLAB using the finite element method. She also developed the coilgun’s control system and implemented laser communication for deep space emulation. Layla is passionate about building intelligent, energy-efficient systems optimized for real-time performance on low-power hardware, which she hopes to apply in meaningful projects that have a real-world impact.

Stephanie Thomas holds bachelor’s and master’s degrees in Aeronautics and Astronautics from MIT. She has nearly 20 years of MATLAB experience, developing tools for solar sails, spacecraft proximity operations and launch vehicle analysis. She contributed to PSS’s Attitude and Orbit Control textbook and authored numerous user guides. Stephanie has trained engineers globally and consulted for NASA, the Air Force, and the European Space Agency. She is a co-author of MATLAB Recipes, MATLAB Machine Learning, and Practical MATLAB Deep Learning Projects. In 2016, she was named a NASA NIAC Fellow for the 'Fusion-Enabled Pluto Orbiter and Lander' project. Stephanie is an Associate Fellow of AIAA and a member of its Propulsion and Energy Group.