Michael Paluszek Bücher

Harness the power of MATLAB for deep-learning challenges. This book provides an introduction to deep learning and using MATLAB's deep-learning toolboxes. You’ll see how these toolboxes provide the complete set of functions needed to implement all aspects of deep learning. Next, you'll learn to model a quadcopter example project in depth. Along the way, you’ll cover dynamics and control, and integrate deep-learning algorithms and approaches using MATLAB. You'll apply deep learning for quadcopter control, sensing, and navigation via simulations. Finally, you'll experience how to fly a hardware quadcopter and then use it for deep-learning experiments to motivate future projects and innovations. What You Will Learn Explore deep learning using MATLAB and compare it to algorithms Write a deep learning function in MATLAB and demonstrate with examples Use MATLAB toolboxes related to deep learning Employ a quadcopter case study throughout book Build the quadcopter Discover the prerequisites for using deep learning with our quadcopter Create quadcopter control, sensing, and navigation via simulations Fly a real hardware quadcopter; use it to carry out additional deep-learning experiments Who This Book Is For Engineers, data scientists, and students wanting a book rich in examples on deep learning using MATLAB.

The book offers a comprehensive exploration of contemporary MATLAB coding, showcasing advanced applications in robotics, motors, detection filters, and chemical processes, as well as in aircraft and spacecraft technology. It emphasizes the latest MATLAB language features and guides readers in using MATLAB as a robust software development environment, covering essential topics such as code organization, GUI development, and effective algorithm design and testing.

Harness the power of MATLAB to resolve a wide range of machine learning challenges. This book provides a series of examples of technologies critical to machine learning. Each example solves a real-world problem. All code in MATLAB Machine Learning Recipes: A Problem-Solution Approach is executable. The toolbox that the code uses provides a complete set of functions needed to implement all aspects of machine learning. Authors Michael Paluszek and Stephanie Thomas show how all of these technologies allow the reader to build sophisticated applications to solve problems with pattern recognition, autonomous driving, expert systems, and much more. What you'll learn: How to write code for machine learning, adaptive control and estimation using MATLAB How these three areas complement each other How these three areas are needed for robust machine learning applications How to use MATLAB graphics and visualization tools for machine learning How to code real world examples in MATLAB for major applications of machine learning in big data Who is this book for: The primary audiences are engineers, data scientists and students wanting a comprehensive and code cookbook rich in examples on machine learning using MATLAB.