Meta-Analytics: Consensus Approaches and System Patterns for Data Analysis

Cover......Page 1
Title......Page 3
Copyright......Page 5
Dedication......Page 6
Acknowledgments......Page 7
Introduction......Page 9
Why is this book important?......Page 10
Organization of the book......Page 11
Informatics......Page 12
Value and variance......Page 13
Sample and population tests......Page 14
Regression and estimation......Page 18
k-Means and k-nearest neighbor clustering......Page 24
Unclustering......Page 27
Markov models......Page 28
Machine learning......Page 30
Entropy......Page 31
SVM and kernels......Page 32
Probability......Page 33
Dimensionality reduction and information gain......Page 35
Optimization and search......Page 36
Data mining and knowledge discovery......Page 38
Recognition......Page 39
Ensemble learning......Page 41
Genetic algorithms......Page 44
Neural networks......Page 50
Immunological algorithms......Page 57
A platform for building a classifier from the ground up (binary case)......Page 60
Training and validation......Page 69
Testing and deployment......Page 79
Comparing training and testing data set results......Page 103
Summary......Page 104
Further reading......Page 106
Introduction......Page 107
Pre-validation......Page 108
Optimizing settings from training data......Page 116
Learning how to Learn......Page 122
Deep learning to deep unlearning......Page 130
Summary......Page 131
References......Page 132
Introduction......Page 133
Simple (unambiguous) normalization......Page 134
Bias normalization......Page 135
Normalization and experimental design tables......Page 140
Designs for the pruning of aging data......Page 141
Systems......Page 143
Hybrid systems......Page 144
Interfaces......Page 146
Gain......Page 147
Domain normalization......Page 150
Sensitivity analysis......Page 151
References......Page 152
Introduction......Page 155
Cumulative response patterns......Page 156
Identifying zones of interest......Page 157
Zones of interest for sequence-dependent predictive selection......Page 160
Traditional cumulative gain curves, or lift curves......Page 162
Decision trees......Page 169
Putative-identity triggered patterns......Page 170
Expectation-maximization and maximum-minimum patterns......Page 172
Model agreement patterns......Page 176
Hybrid regression......Page 177
Modeling and model fitting......Page 178
Co-occurrence and similarity patterns......Page 179
Confusion matrix patterns......Page 181
Entropy patterns......Page 183
Independence pattern......Page 186
Functional NLP patterns (macro-feedback)......Page 190
Summary......Page 191
References......Page 192
Introduction......Page 195
Sensitivity analysis of the data set itself......Page 198
Sensitivity analysis of the individual algorithms......Page 202
Sensitivity analysis of the hybrid algorithmics......Page 204
Sensitivity analysis of the path to the current state......Page 206
Summary......Page 208
References......Page 209
Introduction......Page 211
Means of predicting......Page 212
Means of selecting......Page 214
Multi-path approach......Page 220
Applications......Page 222
Summary......Page 223
Reference......Page 224
Introduction......Page 225
Chemistry analogues for analytics......Page 226
Organic chemistry analogues for analytics......Page 228
Immunological and biological analogues for analytics......Page 230
Anonymization analogues for model design and fitting......Page 232
LSE, error variance, and entropy: Goodness of fit......Page 233
Make mine multiple models!......Page 234
Summary......Page 235
References......Page 236
Introduction......Page 237
Synonym-antonym patterns......Page 238
Reinforce-void patterns......Page 239
Broader applicability of these patterns......Page 243
Further reading......Page 244
Introduction......Page 245
Entropy and occurrence vectors......Page 246
Functional metrics......Page 250
E-M (expectation-maximization) approaches......Page 252
System design concerns......Page 253
Optimizing settings from training data......Page 254
Hybrid methods......Page 255
Summary......Page 257
References......Page 258
Further reading......Page 259
Introduction......Page 261
System considerations-Revisiting the system gains......Page 262
System gains-Revisiting and expanding the system biases......Page 264
Module optimization......Page 268
Clustering and regularization......Page 269
Sum of squares regularization......Page 273
Variance regularization......Page 274
Cluster size regularization......Page 275
Number of clusters regularization......Page 276
Discussion of regularization methods......Page 277
Analytic system optimization......Page 278
References......Page 279
Introduction......Page 281
Sequential removal of features aleatory pattern......Page 283
Sequential variation of feature output aleatory pattern......Page 286
Adding random elements for testing......Page 288
Hyperspectral aleatory approaches......Page 290
Other aleatory applications in machine and statistical learning......Page 291
Summary......Page 292
Further reading......Page 293
Introduction......Page 295
Machine translation......Page 296
Robotics......Page 299
Biological sciences......Page 303
Summary......Page 305
References......Page 306
Introduction......Page 307
Healthcare......Page 308
Economics......Page 310
Business and finance......Page 313
Postscript: Psychology......Page 316
References......Page 318
Chapter 1......Page 319
Chapter 2......Page 320
Chapter 4......Page 321
Chapter 5......Page 322
Chapter 7......Page 323
Chapter 9......Page 324
Chapter 10......Page 325
Chapter 12......Page 326
The future of meta-analytics......Page 327
C......Page 329
E......Page 330
L......Page 331
P......Page 332
S......Page 333
Z......Page 334