## Book description

MACHINE AND DEEP LEARNING

In-depth resource covering machine and deep learning methods using MATLAB tools and algorithms, providing insights and algorithmic decision-making processes

Machine and Deep Learning Using MATLAB introduces early career professionals to the power of MATLAB to explore machine and deep learning applications by explaining the relevant MATLAB tool or app and how it is used for a given method or a collection of methods. Its properties, in terms of input and output arguments, are explained, the limitations or applicability is indicated via an accompanied text or a table, and a complete running example is shown with all needed MATLAB command prompt code.

The text also presents the results, in the form of figures or tables, in parallel with the given MATLAB code, and the MATLAB written code can be later used as a template for trying to solve new cases or datasets. Throughout, the text features worked examples in each chapter for self-study with an accompanying website providing solutions and coding samples. Highlighted notes draw the attention of the user to critical points or issues.

Readers will also find information on:

• Numeric data acquisition and analysis in the form of applying computational algorithms to predict the numeric data patterns (clustering or unsupervised learning)
• Relationships between predictors and response variable (supervised), categorically sub-divided into classification (discrete response) and regression (continuous response)
• Image acquisition and analysis in the form of applying one of neural networks, and estimating net accuracy, net loss, and/or RMSE for the successive training, validation, and testing steps
• Retraining and creation for image labeling, object identification, regression classification, and text recognition

Machine and Deep Learning Using MATLAB is a useful and highly comprehensive resource on the subject for professionals, advanced students, and researchers who have some familiarity with MATLAB and are situated in engineering and scientific fields, who wish to gain mastery over the software and its numerous applications.

1. Cover
2. Title Page
4. Preface
6. 1 Unsupervised Machine Learning (ML) Techniques
1. Introduction
2. Selection of the Right Algorithm in ML
3. Classical Multidimensional Scaling of Predictors Data
4. Principal Component Analysis (PCA)
5. k-Means Clustering
6. Gaussian Mixture Model (GMM) Clustering
7. Observations and Clusters Visualization
8. Evaluating Cluster Quality
9. Hierarchical Clustering
10. PCA and Clustering: Wine Quality
11. Feature Selection Using Laplacian (fsulaplacian) for Unsupervised Learning
12. CHW 1.1 The Iris Flower Features Data
13. CHW 1.2 The Ionosphere Data Features
14. CHW 1.3 The Small Car Data
15. CHW 1.4 Seeds Features Data
7. 2 ML Supervised Learning: Classification Models
1. Fitting Data Using Different Classification Models
2. KNN Model for All Categorical or All Numeric Data Type
3. Using MATLAB Classification Learner
4. Binary Decision Tree Model for Multiclass Classification of All Data Types
5. Naïve Bayes Classification Model for All Data Types
6. Discriminant Analysis (DA) Classifier for Numeric Predictors Only
7. Support Vector Machine (SVM) Classification Model for All Data Types
8. Multiclass Support Vector Machine (fitcecoc) Model
9. Binary Linear Classifier (fitclinear) to High-Dimensional Data
8. 3 Methods of Improving ML Predictive Models
1. Accuracy and Robustness of Predictive Models
2. Reducing Predictors: Feature Transformation and Selection
3. Accommodating Categorical Data: Creating Dummy Variables
4. Ensemble Learning
5. Using MATLAB Regression Learner
6. Feature Selection Using Neighborhood Component Analysis (NCA) for Regression: Big Car Data
7. CHW 3.1 The Ionosphere Data
8. CHW 3.2 Sonar Dataset
9. CHW 3.3 White Wine Classification
10. CHW 3.4 Small Car Data (Regression Case)
9. 4 Methods of ML Linear Regression
1. Introduction
2. Linear Regression Models
3. Nonparametric Regression Models
4. Regularized Parametric Linear Regression
5. Stepwise Parametric Linear Regression
6. CHW 4.1 Boston House Price
7. CHW 4.2 The Forest Fires Data
8. CHW 4.3 The Parkinson’s Disease Telemonitoring Data
9. CHW 4.4 The Car Fuel Economy Data
10. 5 Neural Networks
11. 6 Pretrained Neural Networks: Transfer Learning
1. Deep Learning: Image Networks
2. Data Stores in MATLAB
3. Image and Augmented Image Datastores
4. Accessing an Image File
5. Retraining: Transfer Learning for Image Recognition
6. Convolutional Neural Network (CNN) Layers: Channels and Activations
7. Features Extraction for Machine Learning
8. Network Object Prediction Explainers
9. HCW 6.1 CNN Retraining for Round Worms Alive or Dead Prediction
10. HCW 6.2 CNN Retraining for Food Images Prediction
11. HCW 6.3 CNN Retraining for Merchandise Data Prediction
12. HCW 6.4 CNN Retraining for Musical Instrument Spectrograms Prediction
13. HCW 6.5 CNN Retraining for Fruit/Vegetable Varieties Prediction
12. 7 A Convolutional Neural Network (CNN) Architecture and Training
1. A Simple CNN Architecture: The Land Satellite Images
2. Training Options
3. Training a CNN for Landcover Dataset
4. Layers and Filters
5. Filters in Convolution Layers
6. Viewing Filters: AlexNet Filters
7. Validation Data
8. Improving Network Performance
9. Image Augmentation: The Flowers Dataset
10. Directed Acyclic Graphs Networks
11. Deep Network Designer (DND)
12. Semantic Segmentation
13. HCW 7.1 CNN Creation for Round Worms Alive or Dead Prediction
14. HCW 7.2 CNN Creation for Food Images Prediction
15. HCW 7.3 CNN Creation for Merchandise Data Prediction
16. HCW 7.4 CNN Creation for Musical Instrument Spectrograms Prediction
17. HCW 7.5 CNN Creation for Chest X-ray Prediction
18. HCW 7.6 Semantic Segmentation Network for CamVid Dataset
13. 8 Regression Classification: Object Detection
1. Preparing Data for Regression
2. Deep Network Designer (DND) for Regression
3. YOLO Object Detectors
4. Object Detection Using R-CNN Algorithms
5. Transfer Learning (Re-Training)
6. R-CNN Creation and Training
7. evaluateDetectionPrecision Function for Precision Metric
8. evaluateDetectionMissRate for Miss Rate Metric
9. HCW 8.1 Testing yolov4ObjectDetector and fasterRCNN Object Detector
10. HCW 8.2 Creation of Two CNN-based yolov4ObjectDetectors
11. HCW 8.3 Creation of GoogleNet-Based Fast R-CNN Object Detector
12. HCW 8.4 Creation of a GoogleNet-Based Faster R-CNN Object Detector
13. HCW 8.5 Calculation of Average Precision and Miss Rate Using GoogleNet-Based Faster R-CNN Object Detector
14. HCW 8.6 Calculation of Average Precision and Miss Rate Using GoogleNet-Based yolov4 Object Detector
15. HCW 8.7 Faster RCNN-based Car Objects Prediction and Calculation of Average Precision for Training and Test Data
14. 9 Recurrent Neural Network (RNN)
15. 10 Image/Video-Based Apps
16. Appendix A Useful MATLAB Functions
17. Index