Practical MATLAB deep learning : a projects-based approach
Author(s)
Bibliographic Information
Practical MATLAB deep learning : a projects-based approach
Apress, c2022
2nd ed
- : pbk
Available at 5 libraries
Note
Includes bibliographical references (p. 319-322) and index
Description and Table of Contents
Description
Harness the power of MATLAB for deep-learning challenges. Practical MATLAB Deep Learning, Second Edition, remains a one-of a-kind book that provides an introduction to deep learning and using MATLAB's deep-learning toolboxes. In this book, you'll see how these toolboxes provide the complete set of functions needed to implement all aspects of deep learning. This edition includes new and expanded projects, and covers generative deep learning and reinforcement learning.
Over the course of the book, you'll learn to model complex systems and apply deep learning to problems in those areas. Applications include:
Aircraft navigation
An aircraft that lands on Titan, the moon of Saturn, using reinforcement learning
Stock market prediction
Natural language processing
Music creation usng generative deep learning
Plasma control
Earth sensor processing for spacecraft
MATLAB Bluetooth data acquisition applied to dance physics
What You Will Learn
Explore deep learning using MATLAB and compare it to algorithms
Write a deep learning function in MATLAB and train it with examples
Use MATLAB toolboxes related to deep learning
Implement tokamak disruption prediction
Now includes reinforcement learning
Who This Book Is For
Engineers, data scientists, and students wanting a book rich in examples on deep learning using MATLAB.
Table of Contents
1. What is deep learning? - no changes except editoriala. Machine learning vs. deep learningb. Approaches to deep learningc. Recurrent deep learningd. Convolutional deep learning2. MATLAB machine and deep learning toolboxesa. Describe the functionality and applications of each toolboxb. Demonstrate MATLAB toolboxes related to Deep Learningc. Include the text toolbox generative toolbox and reinforcement learning toolboxd. Add more detail on each3. Finding Circles - no changes except editorial.4. Classifying movies - no changes except editorial.5. Tokamak disruption detection - this would be updated.6. Classifying a pirouette - no changes except editorial.7. Completing sentences - This would be revamped using the MATLAB Text Processing Toolbox.8. Terrain based navigation-The example in the original book would be changed to a regression approach that can interpolate position. We would switch to a terrestrial example applicable to drones.9. Stock prediction - this is a very popular chapter. We would improve the algorithm.10. Image classification - no changes except editorial.11. Orbit Determination - add inclination to the algorithm.12. Earth Sensors - a new example on how to use neural networks to measure roll and yaw from any Earth sensor.13. Generative deep learning example. This would be a neural network that generates pictures after learning an artist's style.14. Reinforcement learning. This would be a simple quadcopter hovering control system. It would be simulation based although readers would be able to apply this to any programmable quadcopter.
by "Nielsen BookData"