{"product_id":"machine-and-deep-learning-using-matlab-algorithms-and-tools-for-scientists-and-engineers-1st-edition","title":"Machine and Deep Learning Using MATLAB: Algorithms and Tools for Scientists and Engineers 1st Edition","description":"\u003cdiv data-cel-widget=\"bookDescription_feature_div\" data-csa-c-id=\"v2qtpm-il6e8f-7s3rfn-6dqbo1\" data-csa-c-is-in-initial-active-row=\"false\" data-csa-c-asin=\"191416119X\" data-csa-c-slot-id=\"bookDescription_feature_div\" data-csa-c-content-id=\"bookDescription\" data-csa-c-type=\"widget\" data-feature-name=\"bookDescription\" class=\"celwidget\" id=\"bookDescription_feature_div\"\u003e\n\u003cdiv class=\"a-expander-collapsed-height a-row a-expander-container a-spacing-base a-expander-partial-collapse-container\" data-a-expander-collapsed-height=\"280\" data-a-expander-name=\"book_description_expander\"\u003e\n\u003cdiv class=\"a-expander-content a-expander-partial-collapse-content\" data-expanded=\"false\"\u003e\n\u003cdiv id=\"bookDescription_feature_div\" class=\"celwidget\" data-feature-name=\"bookDescription\" data-csa-c-type=\"widget\" data-csa-c-content-id=\"bookDescription\" data-csa-c-slot-id=\"bookDescription_feature_div\" data-csa-c-asin=\"1119502012\" data-csa-c-is-in-initial-active-row=\"false\" data-csa-c-id=\"vdza35-7pewfj-mdn14k-p4qlnn\" data-cel-widget=\"bookDescription_feature_div\"\u003e\n\u003cdiv data-a-expander-name=\"book_description_expander\" data-a-expander-collapsed-height=\"280\" class=\"a-expander-collapsed-height a-row a-expander-container a-spacing-base a-expander-partial-collapse-container\"\u003e\n\u003cdiv data-expanded=\"false\" class=\"a-expander-content a-expander-partial-collapse-content\"\u003e\n\u003cdiv id=\"bookDescription_feature_div\" class=\"celwidget\" data-feature-name=\"bookDescription\" data-csa-c-type=\"widget\" data-csa-c-content-id=\"bookDescription\" data-csa-c-slot-id=\"bookDescription_feature_div\" data-csa-c-asin=\"1630814601\" data-csa-c-is-in-initial-active-row=\"false\" data-csa-c-id=\"2pb4pz-rn4ngw-xe19ei-safoql\" data-cel-widget=\"bookDescription_feature_div\"\u003e\n\u003cdiv data-a-expander-name=\"book_description_expander\" data-a-expander-collapsed-height=\"280\" class=\"a-expander-collapsed-height a-row a-expander-container a-spacing-base a-expander-partial-collapse-container\"\u003e\n\u003cdiv data-expanded=\"false\" class=\"a-expander-content a-expander-partial-collapse-content\"\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cspan class=\"a-text-bold\"\u003eIn-depth resource covering machine and deep learning methods using MATLAB tools and algorithms, providing insights and algorithmic decision-making processes\u003c\/span\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan class=\"a-text-italic\"\u003eMachine and Deep Learning Using MATLAB\u003c\/span\u003e\u003cspan\u003e 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.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe 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.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eReaders will also find information on:\u003c\/span\u003e\u003c\/p\u003e\n\u003cul class=\"a-unordered-list a-vertical\"\u003e\n\u003cli\u003e\u003cspan class=\"a-list-item\"\u003e\u003cspan\u003eNumeric data acquisition and analysis in the form of applying computational algorithms to predict the numeric data patterns (clustering or unsupervised learning)\u003c\/span\u003e\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan class=\"a-list-item\"\u003e\u003cspan\u003eRelationships between predictors and response variable (supervised), categorically sub-divided into classification (discrete response) and regression (continuous response)\u003c\/span\u003e\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan class=\"a-list-item\"\u003e\u003cspan\u003eImage 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\u003c\/span\u003e\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan class=\"a-list-item\"\u003e\u003cspan\u003eRetraining and creation for image labeling, object identification, regression classification, and text recognition\u003c\/span\u003e\u003c\/span\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan class=\"a-text-italic\"\u003eMachine and Deep Learning Using MATLAB\u003c\/span\u003e\u003cspan\u003e 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.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cdiv id=\"aboutauthors-section\" class=\"aboutauthors-section\"\u003e\n\u003cdiv class=\"page-section\"\u003e\n\u003cdiv data-toggle=\"collapse\" class=\"section-title collapsed\"\u003eAbout the Author\u003c\/div\u003e\n\u003cdiv class=\"section-content collapsed\"\u003e\n\u003cp\u003e\u003cb\u003eKamal I. M. Al-Malah\u003c\/b\u003e\u003cspan\u003e \u003c\/span\u003ereceived his PhD degree from Oregon State University in 1993. He served as a Professor of Chemical Engineering in Jordan and Gulf countries, as well as Former Chairman of the Chemical Engineering Department at the University of Hail in Saudi Arabia. Professor Al-Malah is an expert in both Aspen Plus\u003csup\u003e®\u003c\/sup\u003e\u003cspan\u003e \u003c\/span\u003eand MATLAB\u003csup\u003e®\u003c\/sup\u003e\u003cspan\u003e \u003c\/span\u003eapplications. He has created a bundle of Windows-based software for engineering applications.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv id=\"permissions-section\" class=\"permissions-section\"\u003e\n\u003cdiv class=\"page-section\"\u003e\n\u003cdiv data-toggle=\"collapse\" class=\"section-title collapsed\"\u003ePermissions\u003c\/div\u003e\n\u003cdiv class=\"section-content collapsed\"\u003e\n\u003cdiv class=\"permissions-content\"\u003e\n\u003ca href=\"https:\/\/s100.copyright.com\/AppDispatchServlet?publisherName=wiley\u0026amp;publication=Book\u0026amp;title=Machine%20and%20Deep%20Learning%20Using%20MATLAB:%20Algorithms%20and%20Tools%20for%20Scientists%20and%20Engineers\u0026amp;bookTitle=Machine%20and%20Deep%20Learning%20Using%20MATLAB:%20Algorithms%20and%20Tools%20for%20Scientists%20and%20Engineers\u0026amp;publicationDate=OCT+2023\u0026amp;author=Kamal%20I.%20M.+Al-Malah\u0026amp;sc=US\u0026amp;numPages=0\u0026amp;copyright=\u0026amp;contentID=978-1-394-20908-8\u0026amp;orderBeanReset=True\" target=\"_blank\"\u003eRequest permission\u003c\/a\u003e\u003cspan\u003e \u003c\/span\u003eto reuse content from this site\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv id=\"tableofcontents-section\" class=\"tableofcontents-section\"\u003e\n\u003cdiv class=\"page-section\"\u003e\n\u003cdiv data-toggle=\"collapse\" class=\"section-title collapsed\"\u003eTable of Contents\u003c\/div\u003e\n\u003cdiv class=\"section-content collapsed\"\u003e\n\u003cp\u003ePreface xiii\u003c\/p\u003e\n\u003cp\u003eAbout the Companion Website xvii\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e1 Unsupervised Machine Learning (ML) Techniques 1\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eIntroduction 1\u003c\/p\u003e\n\u003cp\u003eSelection of the Right Algorithm in ML 2\u003c\/p\u003e\n\u003cp\u003eClassical Multidimensional Scaling of Predictors Data 2\u003c\/p\u003e\n\u003cp\u003ePrincipal Component Analysis (PCA) 6\u003c\/p\u003e\n\u003cp\u003e\u003ci\u003ek\u003c\/i\u003e-Means Clustering 13\u003c\/p\u003e\n\u003cp\u003eDistance Metrics: Locations of Cluster Centroids 13\u003c\/p\u003e\n\u003cp\u003eReplications 14\u003c\/p\u003e\n\u003cp\u003eGaussian Mixture Model (GMM) Clustering 15\u003c\/p\u003e\n\u003cp\u003eOptimum Number of GMM Clusters 17\u003c\/p\u003e\n\u003cp\u003eObservations and Clusters Visualization 18\u003c\/p\u003e\n\u003cp\u003eEvaluating Cluster Quality 21\u003c\/p\u003e\n\u003cp\u003eSilhouette Plots 22\u003c\/p\u003e\n\u003cp\u003eHierarchical Clustering 23\u003c\/p\u003e\n\u003cp\u003eStep 1 -- Determine Hierarchical Structure 23\u003c\/p\u003e\n\u003cp\u003eStep 2 -- Divide Hierarchical Tree into Clusters 25\u003c\/p\u003e\n\u003cp\u003ePCA and Clustering: Wine Quality 27\u003c\/p\u003e\n\u003cp\u003eFeature Selection Using Laplacian (fsulaplacian) for Unsupervised Learning 35\u003c\/p\u003e\n\u003cp\u003eCHW 1.1 The Iris Flower Features Data 37\u003c\/p\u003e\n\u003cp\u003eCHW 1.2 The Ionosphere Data Features 38\u003c\/p\u003e\n\u003cp\u003eCHW 1.3 The Small Car Data 39\u003c\/p\u003e\n\u003cp\u003eCHW 1.4 Seeds Features Data 40\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e2 ML Supervised Learning: Classification Models 42\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eFitting Data Using Different Classification Models 42\u003c\/p\u003e\n\u003cp\u003eCustomizing a Model 43\u003c\/p\u003e\n\u003cp\u003eCreating Training and Test Datasets 43\u003c\/p\u003e\n\u003cp\u003ePredicting the Response 45\u003c\/p\u003e\n\u003cp\u003eEvaluating the Classification Model 45\u003c\/p\u003e\n\u003cp\u003eKNN Model for All Categorical or All Numeric Data Type 47\u003c\/p\u003e\n\u003cp\u003eKNN Model: Heart Disease Numeric Data 48\u003c\/p\u003e\n\u003cp\u003eViewing the Fitting Model Properties 50\u003c\/p\u003e\n\u003cp\u003eThe Fitting Model: Number of Neighbors and Weighting Factor 51\u003c\/p\u003e\n\u003cp\u003eThe Cost Penalty of the Fitting Model 52\u003c\/p\u003e\n\u003cp\u003eKNN Model: Red Wine Data 55\u003c\/p\u003e\n\u003cp\u003eUsing MATLAB Classification Learner 57\u003c\/p\u003e\n\u003cp\u003eBinary Decision Tree Model for Multiclass Classification of All Data Types 68\u003c\/p\u003e\n\u003cp\u003eClassification Tree Model: Heart Disease Numeric Data Types 70\u003c\/p\u003e\n\u003cp\u003eClassification Tree Model: Heart Disease All Predictor Data Types 72\u003c\/p\u003e\n\u003cp\u003eNaive Bayes Classification Model for All Data Types 74\u003c\/p\u003e\n\u003cp\u003eFitting Heart Disease Numeric Data to Naive Bayes Model 75\u003c\/p\u003e\n\u003cp\u003eFitting Heart Disease All Data Types to Naive Bayes Model 77\u003c\/p\u003e\n\u003cp\u003eDiscriminant Analysis (DA) Classifier for Numeric Predictors Only 79\u003c\/p\u003e\n\u003cp\u003eDiscriminant Analysis (DA): Heart Disease Numeric Predictors 82\u003c\/p\u003e\n\u003cp\u003eSupport Vector Machine (SVM) Classification Model for All Data Types 84\u003c\/p\u003e\n\u003cp\u003eProperties of SVM Model 85\u003c\/p\u003e\n\u003cp\u003eSVM Classification Model: Heart Disease Numeric Data Types 87\u003c\/p\u003e\n\u003cp\u003eSVM Classification Model: Heart Disease All Data Types 90\u003c\/p\u003e\n\u003cp\u003eMulticlass Support Vector Machine (fitcecoc) Model 92\u003c\/p\u003e\n\u003cp\u003eMulticlass Support Vector Machines Model: Red Wine Data 95\u003c\/p\u003e\n\u003cp\u003eBinary Linear Classifier (fitclinear) to High-Dimensional Data 98\u003c\/p\u003e\n\u003cp\u003eCHW 2.1 Mushroom Edibility Data 100\u003c\/p\u003e\n\u003cp\u003eCHW 2.2 1994 Adult Census Income Data 100\u003c\/p\u003e\n\u003cp\u003eCHW 2.3 White Wine Classification 101\u003c\/p\u003e\n\u003cp\u003eCHW 2.4 Cardiac Arrhythmia Data 102\u003c\/p\u003e\n\u003cp\u003eCHW 2.5 Breast Cancer Diagnosis 102\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e3 Methods of Improving ML Predictive Models 103\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eAccuracy and Robustness of Predictive Models 103\u003c\/p\u003e\n\u003cp\u003eEvaluating a Model: Cross-Validation 104\u003c\/p\u003e\n\u003cp\u003eCross-Validation Tune-up Parameters 105\u003c\/p\u003e\n\u003cp\u003ePartition with K-Fold: Heart Disease Data Classification 106\u003c\/p\u003e\n\u003cp\u003eReducing Predictors: Feature Transformation and Selection 108\u003c\/p\u003e\n\u003cp\u003eFactor Analysis 110\u003c\/p\u003e\n\u003cp\u003eFeature Transformation and Factor Analysis: Heart Disease Data 113\u003c\/p\u003e\n\u003cp\u003eFeature Selection 115\u003c\/p\u003e\n\u003cp\u003eFeature Selection Using predictorImportance Function: Health Disease Data 116\u003c\/p\u003e\n\u003cp\u003eSequential Feature Selection (SFS): sequentialfs Function with Model Error Handler 118\u003c\/p\u003e\n\u003cp\u003eAccommodating Categorical Data: Creating Dummy Variables 121\u003c\/p\u003e\n\u003cp\u003eFeature Selection with Categorical Heart Disease Data 122\u003c\/p\u003e\n\u003cp\u003eEnsemble Learning 126\u003c\/p\u003e\n\u003cp\u003eCreating Ensembles: Heart Disease Data 130\u003c\/p\u003e\n\u003cp\u003eEnsemble Learning: Wine Quality Classification 131\u003c\/p\u003e\n\u003cp\u003eImproving fitcensemble Predictive Model: Abalone Age Prediction 132\u003c\/p\u003e\n\u003cp\u003eImproving fitctree Predictive Model with Feature Selection (FS): Credit Ratings Data 134\u003c\/p\u003e\n\u003cp\u003eImproving fitctree Predictive Model with Feature Transformation (FT): Credit Ratings Data 135\u003c\/p\u003e\n\u003cp\u003eUsing MATLAB Regression Learner 136\u003c\/p\u003e\n\u003cp\u003eFeature Selection and Feature Transformation Using Regression Learner App 145\u003c\/p\u003e\n\u003cp\u003eFeature Selection Using Neighborhood Component Analysis (NCA) for Regression: Big Car Data 146\u003c\/p\u003e\n\u003cp\u003eCHW 3.1 The Ionosphere Data 148\u003c\/p\u003e\n\u003cp\u003eCHW 3.2 Sonar Dataset 149\u003c\/p\u003e\n\u003cp\u003eCHW 3.3 White Wine Classification 150\u003c\/p\u003e\n\u003cp\u003eCHW 3.4 Small Car Data (Regression Case) 152\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e4 Methods of ML Linear Regression 153\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eIntroduction 153\u003c\/p\u003e\n\u003cp\u003eLinear Regression Models 154\u003c\/p\u003e\n\u003cp\u003eFitting Linear Regression Models Using fitlm Function 155\u003c\/p\u003e\n\u003cp\u003eHow to Organize the Data? 155\u003c\/p\u003e\n\u003cp\u003eResults Visualization: Big Car Data 162\u003c\/p\u003e\n\u003cp\u003eFitting Linear Regression Models Using fitglm Function 164\u003c\/p\u003e\n\u003cp\u003eNonparametric Regression Models 166\u003c\/p\u003e\n\u003cp\u003efitrtree Nonparametric Regression Model: Big Car Data 167\u003c\/p\u003e\n\u003cp\u003eSupport Vector Machine, fitrsvm, Nonparametric Regression Model: Big Car Data 170\u003c\/p\u003e\n\u003cp\u003eNonparametric Regression Model: Gaussian Process Regression (GPR) 172\u003c\/p\u003e\n\u003cp\u003eRegularized Parametric Linear Regression 176\u003c\/p\u003e\n\u003cp\u003eRidge Linear Regression: The Penalty Term 176\u003c\/p\u003e\n\u003cp\u003eFitting Ridge Regression Models 177\u003c\/p\u003e\n\u003cp\u003ePredicting Response Using Ridge Regression Models 178\u003c\/p\u003e\n\u003cp\u003eDetermining Ridge Regression Parameter, λ 179\u003c\/p\u003e\n\u003cp\u003eThe Ridge Regression Model: Big Car Data 179\u003c\/p\u003e\n\u003cp\u003eThe Ridge Regression Model with Optimum λ: Big Car Data 181\u003c\/p\u003e\n\u003cp\u003eRegularized Parametric Linear Regression Model: Lasso 183\u003c\/p\u003e\n\u003cp\u003eStepwise Parametric Linear Regression 186\u003c\/p\u003e\n\u003cp\u003eFitting Stepwise Linear Regression 187\u003c\/p\u003e\n\u003cp\u003eHow to Specify stepwiselm Model? 187\u003c\/p\u003e\n\u003cp\u003eStepwise Linear Regression Model: Big Car Data 188\u003c\/p\u003e\n\u003cp\u003eCHW 4.1 Boston House Price 192\u003c\/p\u003e\n\u003cp\u003eCHW 4.2 The Forest Fires Data 193\u003c\/p\u003e\n\u003cp\u003eCHW 4.3 The Parkinson’s Disease Telemonitoring Data 194\u003c\/p\u003e\n\u003cp\u003eCHW 4.4 The Car Fuel Economy Data 195\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e5 Neural Networks 197\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eIntroduction 197\u003c\/p\u003e\n\u003cp\u003eFeed-Forward Neural Networks 198\u003c\/p\u003e\n\u003cp\u003eFeed-Forward Neural Network Classification 199\u003c\/p\u003e\n\u003cp\u003eFeed-Forward Neural Network Regression 200\u003c\/p\u003e\n\u003cp\u003eNumeric Data: Dummy Variables 200\u003c\/p\u003e\n\u003cp\u003eNeural Network Pattern Recognition (nprtool) Application 201\u003c\/p\u003e\n\u003cp\u003eCommand-Based Feed-Forward Neural Network Classification: Heart Data 210\u003c\/p\u003e\n\u003cp\u003eNeural Network Regression (nftool) 214\u003c\/p\u003e\n\u003cp\u003eCommand-Based Feed-Forward Neural Network Regression: Big Car Data 223\u003c\/p\u003e\n\u003cp\u003eTraining the Neural Network Regression Model Using fitrnet Function: Big Car Data 226\u003c\/p\u003e\n\u003cp\u003eFinding the Optimum Regularization Strength for Neural Network Using Cross-Validation: Big Car Data 229\u003c\/p\u003e\n\u003cp\u003eCustom Hyperparameter Optimization in Neural Network Regression: Big Car Data 231\u003c\/p\u003e\n\u003cp\u003eCHW 5.1 Mushroom Edibility Data 233\u003c\/p\u003e\n\u003cp\u003eCHW 5.2 1994 Adult Census Income Data 233\u003c\/p\u003e\n\u003cp\u003eCHW 5.3 Breast Cancer Diagnosis 234\u003c\/p\u003e\n\u003cp\u003eCHW 5.4 Small Car Data (Regression Case) 234\u003c\/p\u003e\n\u003cp\u003eCHW 5.5 Boston House Price 235\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e6 Pretrained Neural Networks: Transfer Learning 237\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eDeep Learning: Image Networks 237\u003c\/p\u003e\n\u003cp\u003eData Stores in MATLAB 241\u003c\/p\u003e\n\u003cp\u003eImage and Augmented Image Datastores 243\u003c\/p\u003e\n\u003cp\u003eAccessing an Image File 246\u003c\/p\u003e\n\u003cp\u003eRetraining: Transfer Learning for Image Recognition 247\u003c\/p\u003e\n\u003cp\u003eConvolutional Neural Network (CNN) Layers: Channels and Activations 256\u003c\/p\u003e\n\u003cp\u003eConvolution 2-D Layer Features via Activations 258\u003c\/p\u003e\n\u003cp\u003eExtraction and Visualization of Activations 261\u003c\/p\u003e\n\u003cp\u003eA 2-D (or 2-D Grouped) Convolutional Layer 264\u003c\/p\u003e\n\u003cp\u003eFeatures Extraction for Machine Learning 267\u003c\/p\u003e\n\u003cp\u003eImage Features in Pretrained Convolutional Neural Networks (CNNs) 268\u003c\/p\u003e\n\u003cp\u003eClassification with Machine Learning 268\u003c\/p\u003e\n\u003cp\u003eFeature Extraction for Machine Learning: Flowers 269\u003c\/p\u003e\n\u003cp\u003ePattern Recognition Network Generation 271\u003c\/p\u003e\n\u003cp\u003eMachine Learning Feature Extraction: Spectrograms 275\u003c\/p\u003e\n\u003cp\u003eNetwork Object Prediction Explainers 278\u003c\/p\u003e\n\u003cp\u003eOcclusion Sensitivity 278\u003c\/p\u003e\n\u003cp\u003eimageLIME Features Explainer 282\u003c\/p\u003e\n\u003cp\u003egradCAM Features Explainer 284\u003c\/p\u003e\n\u003cp\u003eHCW 6.1 CNN Retraining for Round Worms Alive or Dead Prediction 286\u003c\/p\u003e\n\u003cp\u003eHCW 6.2 CNN Retraining for Food Images Prediction 286\u003c\/p\u003e\n\u003cp\u003eHCW 6.3 CNN Retraining for Merchandise Data Prediction 287\u003c\/p\u003e\n\u003cp\u003eHCW 6.4 CNN Retraining for Musical Instrument Spectrograms Prediction 288\u003c\/p\u003e\n\u003cp\u003eHCW 6.5 CNN Retraining for Fruit\/Vegetable Varieties Prediction 289\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e7 A Convolutional Neural Network (CNN) Architecture and Training 290\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eA Simple CNN Architecture: The Land Satellite Images 291\u003c\/p\u003e\n\u003cp\u003eDisplaying Satellite Images 291\u003c\/p\u003e\n\u003cp\u003eTraining Options 294\u003c\/p\u003e\n\u003cp\u003eMini Batches 295\u003c\/p\u003e\n\u003cp\u003eLearning Rates 296\u003c\/p\u003e\n\u003cp\u003eGradient Clipping 297\u003c\/p\u003e\n\u003cp\u003eAlgorithms 298\u003c\/p\u003e\n\u003cp\u003eTraining a CNN for Landcover Dataset 299\u003c\/p\u003e\n\u003cp\u003eLayers and Filters 302\u003c\/p\u003e\n\u003cp\u003eFilters in Convolution Layers 307\u003c\/p\u003e\n\u003cp\u003eViewing Filters: AlexNet Filters 308\u003c\/p\u003e\n\u003cp\u003eValidation Data 311\u003c\/p\u003e\n\u003cp\u003eUsing shuffle Function 316\u003c\/p\u003e\n\u003cp\u003eImproving Network Performance 319\u003c\/p\u003e\n\u003cp\u003eTraining Algorithm Options 319\u003c\/p\u003e\n\u003cp\u003eTraining Data 319\u003c\/p\u003e\n\u003cp\u003eArchitecture 320\u003c\/p\u003e\n\u003cp\u003eImage Augmentation: The Flowers Dataset 322\u003c\/p\u003e\n\u003cp\u003eDirected Acyclic Graphs Networks 329\u003c\/p\u003e\n\u003cp\u003eDeep Network Designer (DND) 333\u003c\/p\u003e\n\u003cp\u003eSemantic Segmentation 342\u003c\/p\u003e\n\u003cp\u003eAnalyze Training Data for Semantic Segmentation 343\u003c\/p\u003e\n\u003cp\u003eCreate a Semantic Segmentation Network 345\u003c\/p\u003e\n\u003cp\u003eTrain and Test the Semantic Segmentation Network 350\u003c\/p\u003e\n\u003cp\u003eHCW 7.1 CNN Creation for Round Worms Alive or Dead Prediction 356\u003c\/p\u003e\n\u003cp\u003eHCW 7.2 CNN Creation for Food Images Prediction 357\u003c\/p\u003e\n\u003cp\u003eHCW 7.3 CNN Creation for Merchandise Data Prediction 358\u003c\/p\u003e\n\u003cp\u003eHCW 7.4 CNN Creation for Musical Instrument Spectrograms Prediction 358\u003c\/p\u003e\n\u003cp\u003eHCW 7.5 CNN Creation for Chest X-ray Prediction 359\u003c\/p\u003e\n\u003cp\u003eHCW 7.6 Semantic Segmentation Network for CamVid Dataset 359\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e8 Regression Classification: Object Detection 361\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003ePreparing Data for Regression 361\u003c\/p\u003e\n\u003cp\u003eModification of CNN Architecture from Classification to Regression 361\u003c\/p\u003e\n\u003cp\u003eRoot-Mean-Square Error 364\u003c\/p\u003e\n\u003cp\u003eAlexNet-Like CNN for Regression: Hand-Written Synthetic Digit Images 364\u003c\/p\u003e\n\u003cp\u003eA New CNN for Regression: Hand-Written Synthetic Digit Images 370\u003c\/p\u003e\n\u003cp\u003eDeep Network Designer (DND) for Regression 374\u003c\/p\u003e\n\u003cp\u003eLoading Image Data 375\u003c\/p\u003e\n\u003cp\u003eGenerating Training Data 375\u003c\/p\u003e\n\u003cp\u003eCreating a Network Architecture 376\u003c\/p\u003e\n\u003cp\u003eImporting Data 378\u003c\/p\u003e\n\u003cp\u003eTraining the Network 378\u003c\/p\u003e\n\u003cp\u003eTest Network 383\u003c\/p\u003e\n\u003cp\u003eYOLO Object Detectors 384\u003c\/p\u003e\n\u003cp\u003eObject Detection Using YOLO v4 386\u003c\/p\u003e\n\u003cp\u003eCOCO-Based Creation of a Pretrained YOLO v4 Object Detector 387\u003c\/p\u003e\n\u003cp\u003eFine-Tuning of a Pretrained YOLO v4 Object Detector 389\u003c\/p\u003e\n\u003cp\u003eEvaluating an Object Detector 394\u003c\/p\u003e\n\u003cp\u003eObject Detection Using R-CNN Algorithms 396\u003c\/p\u003e\n\u003cp\u003eR-CNN 397\u003c\/p\u003e\n\u003cp\u003eFast R-CNN 397\u003c\/p\u003e\n\u003cp\u003eFaster R-CNN 398\u003c\/p\u003e\n\u003cp\u003eTransfer Learning (Re-Training) 399\u003c\/p\u003e\n\u003cp\u003eR-CNN Creation and Training 399\u003c\/p\u003e\n\u003cp\u003eFast R-CNN Creation and Training 403\u003c\/p\u003e\n\u003cp\u003eFaster R-CNN Creation and Training 408\u003c\/p\u003e\n\u003cp\u003eevaluateDetectionPrecision Function for Precision Metric 413\u003c\/p\u003e\n\u003cp\u003eevaluateDetectionMissRate for Miss Rate Metric 417\u003c\/p\u003e\n\u003cp\u003eHCW 8.1 Testing yolov4ObjectDetector and fasterRCNN Object Detector 424\u003c\/p\u003e\n\u003cp\u003eHCW 8.2 Creation of Two CNN-based yolov4ObjectDetectors 424\u003c\/p\u003e\n\u003cp\u003eHCW 8.3 Creation of GoogleNet-Based Fast R-CNN Object Detector 425\u003c\/p\u003e\n\u003cp\u003eHCW 8.4 Creation of a GoogleNet-Based Faster R-CNN Object Detector 426\u003c\/p\u003e\n\u003cp\u003eHCW 8.5 Calculation of Average Precision and Miss Rate Using GoogleNet-Based Faster R-CNN Object Detector 427\u003c\/p\u003e\n\u003cp\u003eHCW 8.6 Calculation of Average Precision and Miss Rate Using GoogleNet-Based yolov4\u003c\/p\u003e\n\u003cp\u003eObject Detector 427\u003c\/p\u003e\n\u003cp\u003eHCW 8.7 Faster RCNN-based Car Objects Prediction and Calculation of Average Precision for Training and Test Data 427\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e9 Recurrent Neural Network (RNN) 430\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eLong Short-Term Memory (LSTM) and BiLSTM Network 430\u003c\/p\u003e\n\u003cp\u003eTrain LSTM RNN Network for Sequence Classification 437\u003c\/p\u003e\n\u003cp\u003eImproving LSTM RNN Performance 441\u003c\/p\u003e\n\u003cp\u003eSequence Length 441\u003c\/p\u003e\n\u003cp\u003eClassifying Categorical Sequences 445\u003c\/p\u003e\n\u003cp\u003eSequence-to-Sequence Regression Using Deep Learning: Turbo Fan Data 446\u003c\/p\u003e\n\u003cp\u003eClassify Text Data Using Deep Learning: Factory Equipment Failure Text Analysis -- 1 453\u003c\/p\u003e\n\u003cp\u003eClassify Text Data Using Deep Learning: Factory Equipment Failure Text Analysis -- 2 462\u003c\/p\u003e\n\u003cp\u003eWord-by-Word Text Generation Using Deep Learning -- 1 465\u003c\/p\u003e\n\u003cp\u003eWord-by-Word Text Generation Using Deep Learning -- 2 473\u003c\/p\u003e\n\u003cp\u003eTrain Network for Time Series Forecasting Using Deep Network Designer (DND) 475\u003c\/p\u003e\n\u003cp\u003eTrain Network with Numeric Features 486\u003c\/p\u003e\n\u003cp\u003eHCW 9.1 Text Classification: Factory Equipment Failure Text Analysis 491\u003c\/p\u003e\n\u003cp\u003eHCW 9.2 Text Classification: Sentiment Labeled Sentences Data Set 492\u003c\/p\u003e\n\u003cp\u003eHCW 9.3 Text Classification: Netflix Titles Data Set 492\u003c\/p\u003e\n\u003cp\u003eHCW 9.4 Text Regression: Video Game Titles Data Set 492\u003c\/p\u003e\n\u003cp\u003eHCW 9.5 Multivariate Classification: Mill Data Set 493\u003c\/p\u003e\n\u003cp\u003eHCW 9.6 Word-by-Word Text Generation Using Deep Learning 494\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e10 Image\/Video-Based Apps 495\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eImage Labeler (IL) App 495\u003c\/p\u003e\n\u003cp\u003eCreating ROI Labels 498\u003c\/p\u003e\n\u003cp\u003eCreating Scene Labels 499\u003c\/p\u003e\n\u003cp\u003eLabel Ground Truth 500\u003c\/p\u003e\n\u003cp\u003eExport Labeled Ground Truth 501\u003c\/p\u003e\n\u003cp\u003eVideo Labeler (VL) App: Ground Truth Data Creation, Training, and Prediction 502\u003c\/p\u003e\n\u003cp\u003eGround Truth Labeler (GTL) App 513\u003c\/p\u003e\n\u003cp\u003eRunning\/Walking Classification with Video Clips using LSTM 520\u003c\/p\u003e\n\u003cp\u003eExperiment Manager (EM) App 526\u003c\/p\u003e\n\u003cp\u003eImage Batch Processor (IBP) App 533\u003c\/p\u003e\n\u003cp\u003eHCW 10.1 Cat Dog Video Labeling, Training, and Prediction -- 1 537\u003c\/p\u003e\n\u003cp\u003eHCW 10.2 Cat Dog Video Labeling, Training, and Prediction -- 2 537\u003c\/p\u003e\n\u003cp\u003eHCW 10.3 EM Hyperparameters of CNN Retraining for Merchandise Data Prediction 538\u003c\/p\u003e\n\u003cp\u003eHCW 10.4 EM Hyperparameters of CNN Retraining for Round Worms Alive or Dead Prediction 539\u003c\/p\u003e\n\u003cp\u003eHCW 10.5 EM Hyperparameters of CNN Retraining for Food Images Prediction 540\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eAppendix A Useful MATLAB Functions 543\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eA.1 Data Transfer from an External Source into MATLAB 543\u003c\/p\u003e\n\u003cp\u003eA.2 Data Import Wizard 543\u003c\/p\u003e\n\u003cp\u003eA.3 Table Operations 544\u003c\/p\u003e\n\u003cp\u003eA.4 Table Statistical Analysis 547\u003c\/p\u003e\n\u003cp\u003eA.5 Access to Table Variables (Column Titles) 547\u003c\/p\u003e\n\u003cp\u003eA.6 Merging Tables with Mixed Columns and Rows 547\u003c\/p\u003e\n\u003cp\u003eA.7 Data Plotting 548\u003c\/p\u003e\n\u003cp\u003eA.8 Data Normalization 549\u003c\/p\u003e\n\u003cp\u003eA.9 How to Scale Numeric Data Columns to Vary Between 0 and 1 549\u003c\/p\u003e\n\u003cp\u003eA.10 Random Split of a Matrix into a Training and Test Set 550\u003c\/p\u003e\n\u003cp\u003eA.11 Removal of NaN Values from a Matrix 550\u003c\/p\u003e\n\u003cp\u003eA.12 How to Calculate the Percent of Truly Judged Class Type Cases for a Binary Class Response 550\u003c\/p\u003e\n\u003cp\u003eA.13 Error Function m-file 551\u003c\/p\u003e\n\u003cp\u003eA.14 Conversion of Categorical into Numeric Dummy Matrix 552\u003c\/p\u003e\n\u003cp\u003eA.15 evaluateFit2 Function 553\u003c\/p\u003e\n\u003cp\u003eA.16 showActivationsForChannel Function 554\u003c\/p\u003e\n\u003cp\u003eA.17 upsampLowRes Function 555\u003c\/p\u003e\n\u003cp\u003eA.18A preprocessData function 555\u003c\/p\u003e\n\u003cp\u003eA.18B preprocessData2 function 555\u003c\/p\u003e\n\u003cp\u003eA.19 processTurboFanDataTrain function 556\u003c\/p\u003e\n\u003cp\u003eA.20 processTurboFanDataTest Function 556\u003c\/p\u003e\n\u003cp\u003eA.21 preprocessText Function 557\u003c\/p\u003e\n\u003cp\u003eA.22 documentGenerationDatastore Function 557\u003c\/p\u003e\n\u003cp\u003eA.23 subset Function for an Image Data Store Partition 560\u003c\/p\u003e\n\u003cp\u003eIndex 561\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv id=\"globalStoreInfoBullets_feature_div\" class=\"celwidget\" data-feature-name=\"globalStoreInfoBullets\" data-csa-c-type=\"widget\" data-csa-c-content-id=\"globalStoreInfoBullets\" data-csa-c-slot-id=\"globalStoreInfoBullets_feature_div\" data-csa-c-asin=\"1630814601\" data-csa-c-is-in-initial-active-row=\"false\" data-csa-c-id=\"uqki6y-6u049-jgya8i-st2ibm\" data-cel-widget=\"globalStoreInfoBullets_feature_div\"\u003e\u003c\/div\u003e\n\u003cdiv id=\"buyingOptionNostosBadge_feature_div\" class=\"celwidget\" data-feature-name=\"buyingOptionNostosBadge\" data-csa-c-type=\"widget\" data-csa-c-content-id=\"buyingOptionNostosBadge\" data-csa-c-slot-id=\"buyingOptionNostosBadge_feature_div\" data-csa-c-asin=\"1630814601\" data-csa-c-is-in-initial-active-row=\"false\" data-csa-c-id=\"fo9brg-cvk5ph-ul23v5-s3kfux\" data-cel-widget=\"buyingOptionNostosBadge_feature_div\"\u003e\u003c\/div\u003e\n\u003cdiv id=\"tellAmazon_feature_div\" class=\"celwidget\" data-feature-name=\"tellAmazon\" data-csa-c-type=\"widget\" data-csa-c-content-id=\"tellAmazon\" data-csa-c-slot-id=\"tellAmazon_feature_div\" data-csa-c-asin=\"1630814601\" data-csa-c-is-in-initial-active-row=\"false\" data-csa-c-id=\"hvcsq1-if034g-9j2dhb-cnx204\" data-cel-widget=\"tellAmazon_feature_div\"\u003e\n\u003cdiv class=\"celwidget c-f\" data-csa-op-log-render=\"\" data-csa-c-content-id=\"DsUnknown\" data-csa-c-slot-id=\"DsUnknown-4\" data-csa-c-type=\"widget\" data-csa-c-painter=\"tell-amazon-desktop-cards\" data-csa-c-id=\"adup90-tr0fd5-r705nq-vlf2fh\" data-cel-widget=\"tell-amazon-desktop_DetailPage_3\"\u003e\n\u003cdiv id=\"CardInstancek4YhtH-46hQCXcEfNW-4ew\" data-card-metrics-id=\"tell-amazon-desktop_DetailPage_3\" data-acp-tracking=\"{}\" data-mix-claimed=\"true\"\u003e\n\u003cdiv data-asin=\"1630814601\" data-marketplace=\"ATVPDKIKX0DER\" data-logged-in=\"true\" class=\"_tell-amazon-desktop_style_tell_amazon_div__1YDZk\"\u003e\u003cbr\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cb\u003eBOOKREAD™ 5-STEP SATISFACTION GUARANTEE\u003c\/b\u003e\u003c\/strong\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003cstrong\u003e1. No Risk, 30-Day Money-Back Guarantee. \u003cbr\u003e2. instant download. No surprises or hidden fees.\u003cbr\u003e3. Safe Payments via Credit\/Debit Card or PayPal® \u003cbr\u003e4. McAfee™ and SSL secured shopping cart.\u003cbr\u003e5. lifetime customer support.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003c!----\u003e","brand":"bookread","offers":[{"title":"PDF","offer_id":56754828804427,"sku":null,"price":29.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1031\/1204\/8971\/files\/81CS5JSXZyL._SL1500.jpg?v=1773064343","url":"https:\/\/bookread.io\/products\/machine-and-deep-learning-using-matlab-algorithms-and-tools-for-scientists-and-engineers-1st-edition","provider":"bookread","version":"1.0","type":"link"}