Data Science and Predictive Analytics: Biomedical and Health Applications using R

Foreword......Page 6
 Genesis......Page 10
 Limitations/Prerequisites......Page 11
 Scope of the Book......Page 12
 Acknowledgements......Page 13
DSPA Application and Use Disclaimer......Page 14
 Biomedical, Biosocial, Environmental, and Health Disclaimer......Page 15
Notations......Page 16
Contents......Page 17
 1.1 DSPA Mission and Objectives......Page 33
  1.2.2 Parkinson´s Disease......Page 34
  1.2.3 Drug and Substance Use......Page 35
  1.2.6 Neurodegeneration......Page 36
  1.2.7 Genetic Forensics: 2013-2016 Ebola Outbreak......Page 37
  1.2.8 Next Generation Sequence (NGS) Analysis......Page 38
  1.2.9 Neuroimaging-Genetics......Page 39
 1.3 Common Characteristics of Big (Biomedical and Health) Data......Page 40
 1.5 Predictive Analytics......Page 41
 1.7 Examples of Data Repositories, Archives, and Services......Page 42
 1.8 DSPA Expectations......Page 43
 2.1 Why Use R?......Page 45
  2.2.3 RStudio GUI Layout......Page 47
 2.3 Help......Page 48
 2.4 Simple Wide-to-Long Data format Translation......Page 49
 2.5 Data Generation......Page 50
 2.6 Input/Output (I/O)......Page 54
 2.7 Slicing and Extracting Data......Page 56
 2.9 Variable Information......Page 57
 2.10 Data Selection and Manipulation......Page 59
 2.11 Math Functions......Page 62
 2.13 Advanced Data Processing......Page 64
 2.14 Strings......Page 69
 2.15 Plotting......Page 71
 2.16 QQ Normal Probability Plot......Page 73
 2.18 Graphics Parameters......Page 77
 2.19 Optimization and model Fitting......Page 79
 2.20 Statistics......Page 80
  2.21.1 Programming......Page 81
 2.22 Data Simulation Primer......Page 82
  2.23.1 HTML SOCR Data Import......Page 88
  2.23.2 R Debugging......Page 89
  2.24.1 Confirm that You Have Installed R/RStudio......Page 92
  2.24.5 Simulation......Page 93
 References......Page 94
 3.1 Saving and Loading R Data Structures......Page 95
 3.2 Importing and Saving Data from CSV Files......Page 96
 3.4 Exploring Numeric Variables......Page 98
 3.5 Measuring the Central Tendency: Mean, Median, Mode......Page 99
 3.6 Measuring Spread: Quartiles and the Five-Number Summary......Page 100
 3.7 Visualizing Numeric Variables: Boxplots......Page 102
 3.8 Visualizing Numeric Variables: Histograms......Page 103
 3.9 Understanding Numeric Data: Uniform and Normal Distributions......Page 104
 3.10 Measuring Spread: Variance and Standard Deviation......Page 105
 3.11 Exploring Categorical Variables......Page 108
 3.12 Exploring Relationships Between Variables......Page 109
 3.13 Missing Data......Page 111
  3.13.1 Simulate Some Real Multivariate Data......Page 116
  3.13.2 TBI Data Example......Page 130
   General Idea of EM Algorithm......Page 154
   EM-Based Imputation......Page 155
   A Simple Manual Implementation of EM-Based Imputation......Page 156
   Plotting Complete and Imputed Data......Page 159
    Comparison......Page 160
 3.14 Parsing Webpages and Visualizing Tabular HTML Data......Page 162
 3.15 Cohort-Rebalancing (for Imbalanced Groups)......Page 167
  3.16.1 Importing Data from SQL Databases......Page 170
  3.16.2 R Code Fragments......Page 171
  3.17.2 Explore some Bivariate  Relations in the Data......Page 172
 References......Page 173
 4.1 Common Questions......Page 174
  4.3.1 Histograms and Density Plots......Page 175
  4.3.2 Pie Chart......Page 178
  4.3.3 Heat Map......Page 180
  4.4.1 Paired Scatter Plots......Page 183
  4.4.2 Jitter Plot......Page 188
  4.4.3 Bar Plots......Page 190
  4.4.4 Trees and Graphs......Page 195
  4.4.5 Correlation Plots......Page 198
  4.5.1 Line Plots Using ggplot......Page 202
  4.5.3 Distributions......Page 204
  4.5.4 2D Kernel Density and 3D Surface Plots......Page 205
  4.5.5 Multiple 2D Image Surface Plots......Page 207
  4.5.6 3D and 4D Visualizations......Page 209
  4.6.1 Hands-on Activity (Health Behavior Risks)......Page 214
   Housing Price Data......Page 218
   Modeling the Home Price Index Data (Fig. 4.48)......Page 220
   Map of the Neighborhoods of Los Angeles (LA)......Page 222
   Latin Letter Frequency in Different Languages......Page 224
  4.7.2 Trees and Graphs......Page 229
 References......Page 230
Chapter 5: Linear Algebra and Matrix Computing......Page 231
  5.1.1 Create Matrices......Page 232
  5.1.2 Adding Columns and Rows......Page 233
  5.3.1 Addition......Page 234
   Matrix Multiplication......Page 235
  5.3.6 Multiplicative Inverse......Page 237
  5.4.1 Linear Models......Page 239
  5.4.2 Solving Systems of Equations......Page 240
  5.4.3 The Identity Matrix......Page 242
 5.5 Scalars, Vectors and Matrices......Page 243
   Mean......Page 245
   Applications of Matrix Algebra: Linear Modeling......Page 246
   Finding Function Extrema (Min/Max) Using Calculus......Page 247
  5.5.2 Least Square Estimation......Page 248
 5.6 Eigenvalues and Eigenvectors......Page 249
 5.8 Matrix Notation (Another View)......Page 250
 5.9 Multivariate Linear Regression......Page 254
 5.10 Sample Covariance Matrix......Page 257
  5.11.3 Matrix Equations......Page 259
  5.11.8 Least Square Estimation......Page 260
 References......Page 261
 6.1 Example: Reducing 2D to 1D......Page 262
 6.2 Matrix Rotations......Page 266
 6.4 Summary (PCA vs. ICA vs. FA)......Page 271
  6.5.1 Principal Components......Page 272
 6.6 Independent Component Analysis (ICA)......Page 279
 6.7 Factor Analysis (FA)......Page 283
 6.8 Singular Value Decomposition (SVD)......Page 285
 6.10 Case Study for Dimension Reduction (Parkinson´s Disease)......Page 287
  6.11.1 Parkinson´s Disease Example......Page 294
 References......Page 295
Chapter 7: Lazy Learning: Classification Using Nearest Neighbors......Page 296
 7.1 Motivation......Page 297
  7.2.1 Distance Function and Dummy Coding......Page 298
  7.2.3 Rescaling of the Features......Page 299
  7.3.1 Step 1: Collecting Data......Page 300
  7.3.2 Step 2: Exploring and Preparing the Data......Page 301
  7.3.3 Normalizing Data......Page 302
  7.3.6 Step 4: Evaluating Model Performance......Page 303
  7.3.7 Step 5: Improving Model Performance......Page 304
  7.3.8 Testing Alternative Values of k......Page 305
  7.3.9 Quantitative Assessment (Tables 7.2 and 7.3)......Page 311
  7.4.2 Parkinson´s Disease......Page 315
 References......Page 316
 8.1 Overview of the Naive Bayes Algorithm......Page 317
 8.3 Bayes Formula......Page 318
 8.4 The Laplace Estimator......Page 320
  8.5.2 Step 2: Exploring and Preparing the Data......Page 321
   Data Preparation: Processing Text Data for Analysis......Page 322
   Data Preparation: Creating Training and Test Datasets......Page 323
   Visualizing Text Data: Word Clouds......Page 325
   Data Preparation: Creating Indicator Features for Frequent Words......Page 326
  8.5.3 Step 3: Training a Model on the Data......Page 327
  8.5.4 Step 4: Evaluating Model Performance......Page 328
  8.5.5 Step 5: Improving Model Performance......Page 329
  8.5.6 Step 6: Compare Naive Bayesian against LDA......Page 330
 8.6 Practice Problem......Page 331
  8.7.1 Explain These Two Concepts......Page 332
 References......Page 333
 9.1 Motivation......Page 334
 9.2 Hands-on Example: Iris Data......Page 335
 9.3 Decision Tree Overview......Page 337
  9.3.1 Divide and Conquer......Page 338
  9.3.2 Entropy......Page 339
  9.3.4 C5.0 Decision Tree Algorithm......Page 340
  9.3.5 Pruning the Decision Tree......Page 342
  9.4.2 Step 2: Exploring and Preparing the Data......Page 343
   Data Preparation: Creating Random Training and Test Datasets......Page 345
  9.4.3 Step 3: Training a Model On the Data......Page 346
  9.4.4 Step 4: Evaluating Model Performance......Page 349
  9.4.5 Step 5: Trial Option......Page 350
  9.4.6 Loading the Misclassification Error Matrix......Page 351
  9.4.7 Parameter Tuning......Page 352
  9.6.1 Separate and Conquer......Page 358
  9.7.1 Step 3: Training a Model on the Data......Page 359
  9.7.2 Step 4: Evaluating Model Performance......Page 360
  9.7.4 Step 5: Alternative Model2......Page 361
 9.8 Practice Problem......Page 364
  9.9.2 Decision Tree Partitioning......Page 369
 References......Page 370
  10.1.1 Simple Linear Regression......Page 371
 10.2 Ordinary Least Squares Estimation......Page 373
  10.2.2 Correlations......Page 375
  10.2.3 Multiple Linear Regression......Page 376
  10.3.2 Step 2: Exploring and Preparing the Data......Page 378
  10.3.4 Visualizing Relationships Among Features: The Scatterplot Matrix......Page 382
  10.3.5 Step 3: Training a Model on the Data......Page 384
  10.3.6 Step 4: Evaluating Model Performance......Page 385
 10.4 Step 5: Improving Model Performance......Page 387
  10.4.1 Model Specification: Adding Non-linear Relationships......Page 395
  10.4.2 Transformation: Converting a Numeric Variable to a Binary Indicator......Page 396
  10.4.3 Model Specification: Adding Interaction Effects......Page 397
  10.5.1 Adding Regression to Trees......Page 399
  10.6.1 Step 2: Exploring and Preparing the Data......Page 400
  10.6.3 Visualizing Decision Trees......Page 401
  10.6.4 Step 4: Evaluating Model Performance......Page 403
  10.6.6 Step 5: Improving Model Performance......Page 404
 10.7 Practice Problem: Heart Attack Data......Page 406
 References......Page 407
  11.1.1 From Biological to Artificial Neurons......Page 408
  11.1.2 Activation Functions......Page 409
  11.1.5 The Number of Nodes in Each Layer......Page 411
  11.1.6 Training Neural Networks with Backpropagation......Page 412
   Variables......Page 413
  11.2.2 Step 2: Exploring and Preparing the Data......Page 414
  11.2.3 Step 3: Training a Model on the Data......Page 416
  11.2.4 Step 4: Evaluating Model Performance......Page 417
  11.2.5 Step 5: Improving Model Performance......Page 418
 11.3 Simple NN Demo: Learning to Compute......Page 419
 11.4 Case Study 2: Google Trends and the Stock Market - Classification......Page 421
 11.5 Support Vector Machines (SVM)......Page 423
   Linearly Separable Data......Page 424
   Non-linearly Separable Data......Page 427
 11.6 Case Study 3: Optical Character Recognition (OCR)......Page 428
  11.6.1 Step 1: Prepare and Explore the Data......Page 429
  11.6.2 Step 2: Training an SVM Model......Page 430
  11.6.3 Step 3: Evaluating Model Performance......Page 431
  11.6.4 Step 4: Improving Model Performance......Page 433
  11.7.2 Step 2: Exploring and Preparing the Data......Page 434
  11.7.3 Step 3: Training a Model on the Data......Page 436
  11.7.4 Step 4: Evaluating Model Performance......Page 437
  11.7.6 Parameter Tuning......Page 438
  11.7.7 Improving the Performance of Gaussian Kernels......Page 440
  11.8.2 Problem 2: Quality of Life and Chronic Disease......Page 441
 11.9 Appendix......Page 445
  11.10.2 Pediatric Schizophrenia Study......Page 446
 References......Page 447
 12.1 Association Rules......Page 448
 12.3 Measuring Rule Importance by Using Support and Confidence......Page 449
 12.4 Building a Set of Rules with the Apriori Principle......Page 450
 12.5 A Toy Example......Page 451
  12.6.2 Step 2: Exploring and Preparing the Data......Page 452
   Visualizing Item Support: Item Frequency Plots......Page 454
   Visualizing Transaction Data: Plotting the Sparse Matrix......Page 455
  12.6.3 Step 3: Training a Model on the Data......Page 457
  12.6.4 Step 4: Evaluating Model Performance......Page 458
   Sorting the Set of Association Rules......Page 460
   Taking Subsets of Association Rules......Page 461
 12.7 Practice Problems: Groceries......Page 463
 12.8 Summary......Page 466
 References......Page 467
 13.1 Clustering as a Machine Learning Task......Page 468
 13.2 Silhouette Plots......Page 471
  13.3.1 Using Distance to Assign and Update Clusters......Page 472
  13.4.1 Step 1: Collecting Data......Page 473
  13.4.2 Step 2: Exploring and Preparing the Data......Page 474
  13.4.3 Step 3: Training a Model on the Data......Page 475
  13.4.4 Step 4: Evaluating Model Performance......Page 476
  13.4.5 Step 5: Usage of Cluster Information......Page 479
 13.5 Model Improvement......Page 480
  13.5.1 Tuning the Parameter k......Page 482
  13.6.1 Step 1: Collecting Data......Page 484
  13.6.2 Step 2: Exploring and Preparing the Data......Page 485
  13.6.3 Step 3: Training a Model on the Data......Page 486
  13.6.4 Step 4: Evaluating Model Performance......Page 487
  13.6.5 Practice Problem: Youth Development......Page 490
 13.7 Hierarchical Clustering......Page 492
 13.8 Gaussian Mixture Models......Page 495
 13.10 Assignments: 13. k-Means Clustering......Page 497
 References......Page 498
 14.1 Measuring the Performance of Classification Methods......Page 499
  14.2.1 Binary Outcomes......Page 501
  14.2.2 Confusion Matrices......Page 502
  14.2.3 Other Measures of Performance Beyond Accuracy......Page 504
  14.2.4 The Kappa (κ) Statistic......Page 505
  14.2.5 Computation of Observed Accuracy and Expected Accuracy......Page 508
  14.2.6 Sensitivity and Specificity......Page 509
  14.2.7 Precision and Recall......Page 510
  14.2.8 The F-Measure......Page 511
 14.3 Visualizing Performance Tradeoffs (ROC Curve)......Page 512
  14.4.1 The Holdout Method......Page 515
  14.4.2 Cross-Validation......Page 516
  14.4.3 Bootstrap Sampling......Page 518
 14.5 Assignment: 14. Evaluation of Model Performance......Page 519
 References......Page 520
 15.2 Using caret for Automated Parameter Tuning......Page 521
  15.2.1 Customizing the Tuning Process......Page 525
  15.2.2 Improving Model Performance with Meta-learning......Page 526
  15.2.3 Bagging......Page 527
  15.2.4 Boosting......Page 529
   Training Random Forests......Page 530
   Evaluating Random Forest Performance......Page 531
  15.2.6 Adaptive Boosting......Page 532
 15.3 Assignment: 15. Improving Model Performance......Page 534
 References......Page 535
 16.1 Working with Specialized Data and Databases......Page 536
  16.1.1 Data Format Conversion......Page 537
  16.1.2 Querying Data in SQL Databases......Page 538
  16.1.3 Real Random Number Generation......Page 544
  16.1.4 Downloading the Complete Text of Web Pages......Page 545
  16.1.5 Reading and Writing XML with the XML Package......Page 546
  16.1.6 Web-Page Data Scraping......Page 547
  16.1.7 Parsing JSON from Web APIs......Page 548
  16.1.8 Reading and Writing Microsoft Excel Spreadsheets Using XLSX......Page 549
  16.2.1 Working with Bioinformatics Data......Page 550
  16.2.2 Visualizing Network Data......Page 551
  16.3.1 Definition......Page 556
   k-Means Clustering......Page 557
   Concept Drift Streams......Page 559
  16.3.5 Printing, Plotting and Saving Streams......Page 560
  16.3.6 Stream Animation......Page 561
  16.3.7 Case-Study: SOCR Knee Pain Data......Page 563
  16.3.8 Data Stream Clustering and Classification (DSC)......Page 565
  16.3.9 Evaluation of Data Stream Clustering......Page 568
 16.4 Optimization and Improving the Computational Performance......Page 569
  16.4.1 Generalizing Tabular Data Structures with dplyr......Page 570
  16.4.3 Creating Disk-Based Data Frames with ff......Page 571
 16.5 Parallel Computing......Page 572
  16.5.2 Parallel Processing with Multiple Cores......Page 573
  16.5.3 Parallelization Using foreach and doParallel......Page 575
  16.6.2 Growing Bigger and Faster Random Forests with bigrf......Page 576
 16.7 Practice Problem......Page 577
  16.8.3 Data Conversion and Parallel Computing......Page 578
 References......Page 579
  17.1.1 Filtering Techniques......Page 580
  17.1.3 Embedded Techniques......Page 581
  17.2.2 Step 2: Exploring and Preparing the Data......Page 582
  17.2.3 Step 3: Training a Model on the Data......Page 583
   Comparing with RFE......Page 587
   Comparing with Stepwise Feature Selection......Page 589
 17.3 Practice Problem......Page 592
  17.4.2 Use the PPMI Dataset......Page 594
 References......Page 595
Chapter 18: Regularized Linear Modeling and Controlled Variable Selection......Page 596
 18.3 Regularized Linear Modeling......Page 597
  18.3.1 Ridge Regression......Page 599
  18.3.2 Least Absolute Shrinkage and Selection Operator (LASSO) Regression......Page 602
 18.4 Linear Regression......Page 605
  18.4.3 Estimating the Prediction Error......Page 606
  18.4.4 Improving the Prediction Accuracy......Page 607
  18.4.5 Variable Selection......Page 608
  18.5.2 Role of the Regularization Parameter......Page 609
  18.5.4 General Regularization Framework......Page 610
  18.6.1 Example: Neuroimaging-Genetics Study of Parkinson´s Disease Dataset......Page 611
  18.6.3 LASSO and Ridge Solution Paths......Page 613
  18.6.4 Choice of the Regularization Parameter......Page 621
  18.6.6 n-Fold Cross Validation......Page 622
  18.6.7 LASSO 10-Fold Cross Validation......Page 623
  18.6.8 Stepwise OLS (Ordinary Least Squares)......Page 624
  18.6.9 Final Models......Page 625
  18.6.11 Comparing Selected Features......Page 627
 18.7 Knock-off Filtering: Simulated Example......Page 628
  18.7.1 Notes......Page 630
  18.8.1 Fetching, Cleaning and Preparing the Data......Page 631
  18.8.2 Preparing the Response Vector......Page 632
  18.8.3 False Discovery Rate (FDR)......Page 640
   Graphical Interpretation of the Benjamini-Hochberg (BH) Method......Page 641
   FDR Adjusting the p-Values......Page 642
  18.8.4 Running the Knockoff Filter......Page 643
 18.9 Assignment: 18. Regularized Linear Modeling and Knockoff Filtering......Page 644
 References......Page 645
 19.1 Time Series Analysis......Page 646
  19.1.1 Step 1: Plot Time Series......Page 649
  19.1.2 Step 2: Find Proper Parameter Values for ARIMA Model......Page 651
  19.1.3 Check the Differencing Parameter......Page 652
  19.1.4 Identifying the AR and MA Parameters......Page 653
  19.1.5 Step 3: Build an ARIMA Model......Page 655
  19.1.6 Step 4: Forecasting with ARIMA Model......Page 660
  19.2.1 Foundations of SEM......Page 661
  19.2.2 SEM Components......Page 664
   Step 2 - Exploring and Preparing the Data......Page 665
   Step 3 - Fitting a Model on the Data......Page 668
  19.2.4 Outputs of Lavaan SEM......Page 670
  19.3.1 Mean Trend......Page 671
  19.3.2 Modeling the Correlation......Page 675
 19.4 GLMM/GEE Longitudinal Data Analysis......Page 676
  19.4.1 GEE Versus GLMM......Page 678
  19.5.1 Imaging Data......Page 680
 References......Page 681
Chapter 20: Natural Language Processing/Text Mining......Page 682
 20.1 A Simple NLP/TM Example......Page 683
  20.1.1 Define and Load the Unstructured-Text Documents......Page 684
  20.1.2 Create a New VCorpus Object......Page 686
   Remove Stopwords......Page 687
   Stemming: Removal of Plurals and Action Suffixes......Page 688
  20.1.5 Bags of Words......Page 689
  20.1.6 Document Term Matrix......Page 690
 20.2 Case-Study: Job Ranking......Page 692
  20.2.3 Step 3: Build the Document Term Matrix......Page 693
  20.2.4 Area Under the ROC Curve......Page 697
  20.3.2 Inverse Document Frequency (IDF)......Page 699
  20.3.3 TF-IDF......Page 700
 20.4 Cosine Similarity......Page 708
  20.5.1 Data Preprocessing......Page 709
  20.5.2 NLP/TM Analytics......Page 712
  20.5.3 Prediction Optimization......Page 715
  20.6.1 Mining Twitter Data......Page 717
 References......Page 718
 21.1 Forecasting Types and Assessment Approaches......Page 719
  21.2.2 Example (Google Flu Trends)......Page 720
  21.2.3 Example (Autism)......Page 722
 21.3 Internal Statistical Cross-Validation is an Iterative Process......Page 723
 21.4 Example (Linear Regression)......Page 724
  21.4.2 Exhaustive Cross-Validation......Page 725
 21.5 Case-Studies......Page 726
  21.5.1 Example 1: Prediction of Parkinson´s Disease Using Adaptive Boosting (AdaBoost)......Page 727
  21.5.2 Example 2: Sleep Dataset......Page 730
  21.5.3 Example 3: Model-Based (Linear Regression) Prediction Using the Attitude Dataset......Page 732
  21.5.4 Example 4: Parkinson´s Data (ppmi_data)......Page 733
 21.7 Alternative Predictor Functions......Page 734
  21.7.1 Logistic Regression......Page 735
  21.7.2 Quadratic Discriminant Analysis (QDA)......Page 736
  21.7.3 Foundation of LDA and QDA for Prediction, Dimensionality Reduction, and Forecasting......Page 737
   QDA (Quadratic Discriminant Analysis)......Page 738
  21.7.4 Neural Networks......Page 739
  21.7.5 SVM......Page 740
  21.7.6 k-Nearest Neighbors Algorithm (k-NN)......Page 741
  21.7.7 k-Means Clustering (k-MC)......Page 742
   Iris Petal Data......Page 749
   Spirals Data......Page 750
   Income Data......Page 751
 21.8 Compare the Results......Page 752
 21.9 Assignment: 21. Prediction and Internal Statistical Cross-Validation......Page 755
 References......Page 756
 22.1 Free (Unconstrained) Optimization......Page 757
  22.1.1 Example 1: Minimizing a Univariate Function (Inverse-CDF)......Page 758
  22.1.2 Example 2: Minimizing a Bivariate Function......Page 760
  22.1.3 Example 3: Using Simulated Annealing to Find the Maximum of an Oscillatory Function......Page 761
  22.2.2 Lagrange Multipliers......Page 762
   Linear Programming (LP)......Page 763
   Mixed Integer Linear Programming (MILP)......Page 768
  22.2.4 Quadratic Programming (QP)......Page 769
 22.3 General Non-linear Optimization......Page 770
   Motivation......Page 771
   Example 1: Linear Example......Page 772
   Example 2: Quadratic Example......Page 773
   Example 3: More Complex Non-linear Optimization......Page 774
 22.4 Manual Versus Automated Lagrange Multiplier Optimization......Page 775
 22.5 Data Denoising......Page 778
  22.6.2 Linear Programming (LP)......Page 783
  22.6.5 Complex Non-linear Optimization......Page 784
 References......Page 785
Chapter 23: Deep Learning, Neural Networks......Page 786
  23.1.1 Perceptrons......Page 787
 23.2 Biological Relevance......Page 789
  23.3.1 Exclusive OR (XOR) Operator......Page 791
  23.3.2 NAND Operator......Page 792
  23.3.3 Complex Networks Designed Using Simple Building Blocks......Page 793
 23.4 Classification......Page 794
  23.4.1 Sonar Data Example......Page 795
  23.4.2 MXNet Notes......Page 802
 23.5 Case-Studies......Page 803
  23.5.1 ALS Regression Example......Page 804
  23.5.2 Spirals 2D Data......Page 806
  23.5.3 IBS Study......Page 810
  23.5.4 Country QoL Ranking Data......Page 813
  23.5.5 Handwritten Digits Classification......Page 816
   Configuring the Neural Network......Page 820
   Forecasting......Page 821
   Examining the Network Structure Using LeNet......Page 825
  23.6.2 Load, Preprocess and Classify New Images - US Weather Pattern......Page 827
  23.6.3 Lake Mapourika, New Zealand......Page 831
  23.6.4 Beach Image......Page 832
  23.6.5 Volcano......Page 833
  23.6.6 Brain Surface......Page 835
  23.6.7 Face Mask......Page 836
  23.7.1 Deep Learning Classification......Page 837
 References......Page 838
Summary......Page 839
Glossary......Page 842
Index......Page 844