Book description
MACHINE AND DEEP LEARNINGIndepth resource covering machine and deep learning methods using MATLAB tools and algorithms, providing insights and algorithmic decisionmaking 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 selfstudy 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 subdivided 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.
Table of contents
 Cover
 Title Page
 Copyright Page
 Preface
 About the Companion Website

1 Unsupervised Machine Learning (ML) Techniques
 Introduction
 Selection of the Right Algorithm in ML
 Classical Multidimensional Scaling of Predictors Data
 Principal Component Analysis (PCA)
 kMeans Clustering
 Gaussian Mixture Model (GMM) Clustering
 Observations and Clusters Visualization
 Evaluating Cluster Quality
 Hierarchical Clustering
 PCA and Clustering: Wine Quality
 Feature Selection Using Laplacian (fsulaplacian) for Unsupervised Learning
 CHW 1.1 The Iris Flower Features Data
 CHW 1.2 The Ionosphere Data Features
 CHW 1.3 The Small Car Data
 CHW 1.4 Seeds Features Data

2 ML Supervised Learning: Classification Models
 Fitting Data Using Different Classification Models
 KNN Model for All Categorical or All Numeric Data Type
 Using MATLAB Classification Learner
 Binary Decision Tree Model for Multiclass Classification of All Data Types
 Naïve Bayes Classification Model for All Data Types
 Discriminant Analysis (DA) Classifier for Numeric Predictors Only
 Support Vector Machine (SVM) Classification Model for All Data Types
 Multiclass Support Vector Machine (fitcecoc) Model
 Binary Linear Classifier (fitclinear) to HighDimensional Data

3 Methods of Improving ML Predictive Models
 Accuracy and Robustness of Predictive Models
 Reducing Predictors: Feature Transformation and Selection
 Accommodating Categorical Data: Creating Dummy Variables

Ensemble Learning
 Creating Ensembles: Heart Disease Data
 Ensemble Learning: Wine Quality Classification
 Improving fitcensemble Predictive Model: Abalone Age Prediction
 Improving fitctree Predictive Model with Feature Selection (FS): Credit Ratings Data
 Improving fitctree Predictive Model with Feature Transformation (FT): Credit Ratings Data
 Using MATLAB Regression Learner
 Feature Selection Using Neighborhood Component Analysis (NCA) for Regression: Big Car Data
 CHW 3.1 The Ionosphere Data
 CHW 3.2 Sonar Dataset
 CHW 3.3 White Wine Classification
 CHW 3.4 Small Car Data (Regression Case)

4 Methods of ML Linear Regression
 Introduction
 Linear Regression Models
 Nonparametric Regression Models

Regularized Parametric Linear Regression
 Ridge Linear Regression: The Penalty Term
 Fitting Ridge Regression Models
 Predicting Response Using Ridge Regression Models
 Determining Ridge Regression Parameter, λ
 The Ridge Regression Model: Big Car Data
 The Ridge Regression Model with Optimum λ: Big Car Data
 Regularized Parametric Linear Regression Model: Lasso
 Stepwise Parametric Linear Regression
 CHW 4.1 Boston House Price
 CHW 4.2 The Forest Fires Data
 CHW 4.3 The Parkinson’s Disease Telemonitoring Data
 CHW 4.4 The Car Fuel Economy Data

5 Neural Networks
 Introduction
 FeedForward Neural Networks
 FeedForward Neural Network Classification
 FeedForward Neural Network Regression
 Neural Network Pattern Recognition (nprtool) Application
 CommandBased FeedForward Neural Network Classification: Heart Data
 Neural Network Regression (nftool)
 CommandBased FeedForward Neural Network Regression: Big Car Data
 Training the Neural Network Regression Model Using fitrnet Function: Big Car Data
 Finding the Optimum Regularization Strength for Neural Network Using CrossValidation: Big Car Data
 Custom Hyperparameter Optimization in Neural Network Regression: Big Car Data
 CHW 5.1 Mushroom Edibility Data
 CHW 5.2 1994 Adult Census Income Data
 CHW 5.3 Breast Cancer Diagnosis
 CHW 5.4 Small Car Data (Regression Case)
 CHW 5.5 Boston House Price

6 Pretrained Neural Networks: Transfer Learning
 Deep Learning: Image Networks
 Data Stores in MATLAB
 Image and Augmented Image Datastores
 Accessing an Image File
 Retraining: Transfer Learning for Image Recognition
 Convolutional Neural Network (CNN) Layers: Channels and Activations
 Features Extraction for Machine Learning
 Network Object Prediction Explainers
 HCW 6.1 CNN Retraining for Round Worms Alive or Dead Prediction
 HCW 6.2 CNN Retraining for Food Images Prediction
 HCW 6.3 CNN Retraining for Merchandise Data Prediction
 HCW 6.4 CNN Retraining for Musical Instrument Spectrograms Prediction
 HCW 6.5 CNN Retraining for Fruit/Vegetable Varieties Prediction

7 A Convolutional Neural Network (CNN) Architecture and Training
 A Simple CNN Architecture: The Land Satellite Images
 Training Options
 Training a CNN for Landcover Dataset
 Layers and Filters
 Filters in Convolution Layers
 Viewing Filters: AlexNet Filters
 Validation Data
 Improving Network Performance
 Image Augmentation: The Flowers Dataset
 Directed Acyclic Graphs Networks
 Deep Network Designer (DND)
 Semantic Segmentation
 HCW 7.1 CNN Creation for Round Worms Alive or Dead Prediction
 HCW 7.2 CNN Creation for Food Images Prediction
 HCW 7.3 CNN Creation for Merchandise Data Prediction
 HCW 7.4 CNN Creation for Musical Instrument Spectrograms Prediction
 HCW 7.5 CNN Creation for Chest Xray Prediction
 HCW 7.6 Semantic Segmentation Network for CamVid Dataset

8 Regression Classification: Object Detection
 Preparing Data for Regression
 Deep Network Designer (DND) for Regression
 YOLO Object Detectors
 Object Detection Using RCNN Algorithms
 Transfer Learning (ReTraining)
 RCNN Creation and Training
 evaluateDetectionPrecision Function for Precision Metric
 evaluateDetectionMissRate for Miss Rate Metric
 HCW 8.1 Testing yolov4ObjectDetector and fasterRCNN Object Detector
 HCW 8.2 Creation of Two CNNbased yolov4ObjectDetectors
 HCW 8.3 Creation of GoogleNetBased Fast RCNN Object Detector
 HCW 8.4 Creation of a GoogleNetBased Faster RCNN Object Detector
 HCW 8.5 Calculation of Average Precision and Miss Rate Using GoogleNetBased Faster RCNN Object Detector
 HCW 8.6 Calculation of Average Precision and Miss Rate Using GoogleNetBased yolov4 Object Detector
 HCW 8.7 Faster RCNNbased Car Objects Prediction and Calculation of Average Precision for Training and Test Data

9 Recurrent Neural Network (RNN)
 Long ShortTerm Memory (LSTM) and BiLSTM Network
 Train LSTM RNN Network for Sequence Classification
 Improving LSTM RNN Performance
 Classifying Categorical Sequences
 SequencetoSequence Regression Using Deep Learning: Turbo Fan Data
 Classify Text Data Using Deep Learning: Factory Equipment Failure Text Analysis – 1
 Classify Text Data Using Deep Learning: Factory Equipment Failure Text Analysis – 2
 WordbyWord Text Generation Using Deep Learning – 1
 WordbyWord Text Generation Using Deep Learning – 2
 Train Network for Time Series Forecasting Using Deep Network Designer (DND)
 Train Network with Numeric Features
 HCW 9.1 Text Classification: Factory Equipment Failure Text Analysis
 HCW 9.2 Text Classification: Sentiment Labeled Sentences Data Set
 HCW 9.3 Text Classification: Netflix Titles Data Set
 HCW 9.4 Text Regression: Video Game Titles Data Set
 HCW 9.5 Multivariate Classification: Mill Data Set
 HCW 9.6 WordbyWord Text Generation Using Deep Learning

10 Image/VideoBased Apps
 Image Labeler (IL) App
 Video Labeler (VL) App: Ground Truth Data Creation, Training, and Prediction
 Ground Truth Labeler (GTL) App
 Running/Walking Classification with Video Clips using LSTM
 Experiment Manager (EM) App
 Image Batch Processor (IBP) App
 HCW 10.1 Cat Dog Video Labeling, Training, and Prediction – 1
 HCW 10.2 Cat Dog Video Labeling, Training, and Prediction – 2
 HCW 10.3 EM Hyperparameters of CNN Retraining for Merchandise Data Prediction
 HCW 10.4 EM Hyperparameters of CNN Retraining for Round Worms Alive or Dead Prediction
 HCW 10.5 EM Hyperparameters of CNN Retraining for Food Images Prediction

Appendix A Useful MATLAB Functions
 A.1 Data Transfer from an External Source into MATLAB
 A.2 Data Import Wizard
 A.3 Table Operations
 A.4 Table Statistical Analysis
 A.5 Access to Table Variables (Column Titles)
 A.6 Merging Tables with Mixed Columns and Rows
 A.7 Data Plotting
 A.8 Data Normalization
 A.9 How to Scale Numeric Data Columns to Vary Between 0 and 1
 A.10 Random Split of a Matrix into a Training and Test Set
 A.11 Removal of NaN Values from a Matrix
 A.12 How to Calculate the Percent of Truly Judged Class Type Cases for a Binary Class Response
 A.13 Error Function mfile
 A.14 Conversion of Categorical into Numeric Dummy Matrix
 A.15 evaluateFit2 Function
 A.16 showActivationsForChannel Function
 A.17 upsampLowRes Function
 A.18A preprocessData function
 A.18B preprocessData2 function
 A.19 processTurboFanDataTrain function
 A.20 processTurboFanDataTest Function
 A.21 preprocessText Function
 A.22 documentGenerationDatastore Function
 A.23 subset Function for an Image Data Store Partition
 Index
 End User License Agreement
Product information
 Title: Machine and Deep Learning Using MATLAB
 Author(s):
 Release date: October 2023
 Publisher(s): Wiley
 ISBN: 9781394209088
You might also like
book
Practical MATLAB Deep Learning: A ProjectsBased Approach
Harness the power of MATLAB for deeplearning challenges. Practical MATLAB Deep Learning, Second Edition, remains a …
book
MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence
Get started with MATLAB for deep learning and AI with this indepth primer. In this book, …
book
Bayesian Optimization: Theory and Practice Using Python
This book covers the essential theory and implementation of popular Bayesian optimization techniques in an intuitive …
book
A Handbook of Mathematical Models with Python
Master the art of mathematical modeling through practical examples, use cases, and machine learning techniques Key …