Practical MATLAB Deep Learning: A Project-Based Approach

✍ Scribed by Michael Paluszek, Stephanie Thomas

• Publisher: Apress
• Year: 2020
• Tongue: English
• Leaves: 260
• Edition: 1
• Category: Library

✦ Synopsis

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. 

Along the way, you'll learn to model complex systems, including the stock market, natural language, and angles-only orbit determination. You’ll cover dynamics and control, and integrate deep-learning algorithms and approaches using MATLAB. You'll also apply deep learning to aircraft navigation using images.  

Finally, you'll carry out classification of ballet pirouettes using an inertial measurement unit to experiment with MATLAB's hardware capabilities.  

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

Who This Book Is For 

Engineers, data scientists, and students wanting a book rich in examples on deep learning using MATLAB.

✦ Table of Contents

Contents
About the Authors
About the Technical Reviewer
Acknowledgements
1
What Is Deep Learning?
1.1 Deep Learning
1.2 History of Deep Learning
1.3 Neural Nets
1.3.1 Daylight Detector
Problem
Solution
How It Works
1.3.2 XOR Neural Net
Problem
Solution
How It Works
1.4 Deep Learning and Data
1.5 Types of Deep Learning
1.5.1 Multilayer Neural Network
1.5.2 Convolutional Neural Networks (CNN)
1.5.3 Recurrent Neural Network (RNN)
1.5.4 Long Short-Term Memory Networks (LSTMs)
1.5.5 Recursive Neural Network
1.5.6 Temporal Convolutional Machines (TCMs)
1.5.7 Stacked Autoencoders
1.5.8 Extreme Learning Machine (ELM)
1.5.9 Recursive Deep Learning
1.5.10 Generative Deep Learning
1.6 Applications of Deep Learning
1.7 Organization of the Book
2
MATLAB Machine Learning Toolboxes
2.1 Commercial MATLAB Software
2.1.1 MathWorks Products
Deep Learning Toolbox
Instrument Control Toolbox
Statistics and Machine Learning Toolbox
Computer Vision System Toolbox
Image Acquisition Toolbox
Parallel Computing Toolbox
Text Analytics Toolbox
2.2 MATLAB Open Source
2.2.1 Deep Learn Toolbox
2.2.2 Deep Neural Network
2.2.3 MatConvNet
2.2.4 Pattern Recognition and Machine Learning Toolbox (PRMLT)
2.3 XOR Example
2.4 Training
2.5 Zermelo's Problem
3
Finding Circles with Deep Learning
3.1 Introduction
3.2 Structure
3.2.1 imageInputLayer
3.2.2 convolution2dLayer
3.2.3 batchNormalizationLayer
3.2.4 reluLayer
3.2.5 maxPooling2dLayer
3.2.6 fullyConnectedLayer
3.2.7 softmaxLayer
3.2.8 classificationLayer
3.2.9 Structuring the Layers
3.3 Generating Data: Ellipses and Circles
3.3.1 Problem
3.3.2 Solution
3.3.3 How It Works
3.4 Training and Testing
3.4.1 Problem
3.4.2 Solution
3.4.3 How It Works
4
Classifying Movies
4.1 Introduction
4.2 Generating a Movie Database
4.2.1 Problem
4.2.2 Solution
4.2.3 How It Works
4.3 Generating a Movie Watcher Database
4.3.1 Problem
4.3.2 Solution
4.3.3 How It Works
4.4 Training and Testing
4.4.1 Problem
4.4.2 Solution
4.4.3 How It Works
5
Algorithmic Deep Learning
5.1 Building a Detection Filter
5.1.1 Problem
5.1.2 Solution
5.1.3 How It Works
5.2 Simulating Fault Detection
5.2.1 Problem
5.2.2 Solution
5.2.3 How It Works
5.3 Testing and Training
5.3.1 Problem
5.3.2 Solution
5.3.3 How It Works
6
Tokamak Disruption Detection
6.1 Introduction
6.2 Numerical Model
6.2.1 Dynamics
6.2.2 Sensors
6.2.3 Disturbances
6.2.4 Controller
6.3 Dynamical Model
6.3.1 Problem
6.3.2 Solution
6.3.3 How It Works
6.4 Simulate the Plasma
6.4.1 Problem
6.4.2 Solution
6.4.3 How It Works
6.5 Control the Plasma
6.5.1 Problem
6.5.2 Solution
6.5.3 How It Works
6.6 Training and Testing
6.6.1 Problem
6.6.2 Solution
6.6.3 How It Works
7
Classifying a Pirouette
7.1 Introduction
7.1.1 Inertial Measurement Unit
7.1.2 Physics
7.2 Data Acquisition
7.2.1 Problem
7.2.2 Solution
7.2.3 How It Works
7.3 Orientation
7.3.1 Problem
7.3.2 Solution
7.3.3 How It Works
7.4 Dancer Simulation
7.4.1 Problem
7.4.2 Solution
7.4.3 How It Works
7.5 Real-Time Plotting
7.5.1 Problem
7.5.2 Solution
7.5.3 How It Works
7.6 Quaternion Display
7.6.1 Problem
7.6.2 Solution
7.6.3 How It Works
7.7 Data Acquisition GUI
7.7.1 Problem
7.7.2 Solution
7.7.3 How It Works
7.8 Making the IMU Belt
7.8.1 Problem
7.8.2 Solution
7.8.3 How It Works
7.9 Testing the System
7.9.1 Problem
7.9.2 Solution
7.9.3 How It Works
7.10 Classifying the Pirouette
7.10.1 Problem
7.10.2 Solution
7.10.3 How It Works
7.11 Hardware Sources
8
Completing Sentences
8.1 Introduction
8.1.1 Sentence Completion
8.1.2 Grammar
8.1.3 Sentence Completion by Pattern Recognition
8.1.4 Sentence Generation
8.2 Generating a Database of Sentences
8.2.1 Problem
8.2.2 Solution
8.2.3 How It Works
8.3 Creating a Numeric Dictionary
8.3.1 Problem
8.3.2 Solution
8.3.3 How It Works
8.4 Map Sentences to Numbers
8.4.1 Problem
8.4.2 Solution
8.4.3 How It Works
8.5 Converting the Sentences
8.5.1 Problem
8.5.2 Solution
8.5.3 How It Works
8.6 Training and Testing
8.6.1 Problem
8.6.2 Solution
8.6.3 How It Works
9
Terrain-Based Navigation
9.1 Introduction
9.2 Modeling Our Aircraft
9.2.1 Problem
9.2.2 Solution
9.2.3 How It Works
9.3 Generating a Terrain Model
9.3.1 Problem
9.3.2 Solution
9.3.3 How It Works
9.4 Close Up Terrain
9.4.1 Problem
9.4.2 Solution
9.4.3 How It Works
9.5 Building the Camera Model
9.5.1 Problem
9.5.2 Solution
9.5.3 How It Works
9.6 Plot Trajectory over an Image
9.6.1 Problem
9.6.2 Solution
9.6.3 How It Works
9.7 Creating the Test Images
9.7.1 Problem
9.7.2 Solution
9.7.3 How It Works
9.8 Training and Testing
9.8.1 Problem
9.8.2 Solution
9.8.3 How It Works
9.9 Simulation
9.9.1 Problem
9.9.2 Solution
9.9.3 How It Works
10
Stock Prediction
10.1 Introduction
10.2 Generating a Stock Market
10.2.1 Problem
10.2.2 Solution
10.2.3 How It Works
10.3 Create a Stock Market
10.3.1 Problem
10.3.2 Solution
10.3.3 How It Works
10.4 Training and Testing
10.4.1 Problem
10.4.2 Solution
10.4.3 How It Works
11
Image Classification
11.1 Introduction
11.2 Using a Pretrained Network
11.2.1 Problem
11.2.2 Solution
11.2.3 How It Works
12
Orbit Determination
12.1 Introduction
12.2 Generating the Orbits
12.2.1 Problem
12.2.2 Solution
12.2.3 How It Works
12.3 Training and Testing
12.3.1 Problem
12.3.2 Solution
12.3.3 How It Works
12.4 Implementing an LSTM
12.4.1 Problem
12.4.2 Solution
12.4.3 How It Works
12.5 Conic Sections
Bibliography
Index