دانلود کتاب Statistics for Machine Learning

فهرست مطالب :

Cover......Page 1
Copyright......Page 3
Credits......Page 5
About the Author......Page 6
About the Reviewer......Page 7
www.PacktPub.com......Page 8
Customer Feedback......Page 9
Table of Contents......Page 10
Preface......Page 15
Chapter 1: Journey from Statistics to Machine Learning......Page 21
Machine learning......Page 22
Major differences between statistical modeling and machine learning......Page 24
Steps in machine learning model development and deployment......Page 25
Statistical fundamentals and terminology for model building and validation......Page 26
Bias versus variance trade-off......Page 46
Train and test data......Page 48
Machine learning terminology for model building and validation......Page 49
Linear regression versus gradient descent......Page 52
Machine learning losses......Page 55
When to stop tuning machine learning models......Page 57
Train, validation, and test data......Page 58
Grid search......Page 60
Machine learning model overview......Page 64
Summary......Page 68
Comparison between regression and machine learning models......Page 69
Compensating factors in machine learning models......Page 71
Assumptions of linear regression......Page 72
Example of simple linear regression from first principles......Page 75
Example of simple linear regression using the wine quality data......Page 78
Example of multilinear regression - step-by-step methodology of model building......Page 80
Backward and forward selection......Page 83
Machine learning models - ridge and lasso regression......Page 89
Example of ridge regression machine learning......Page 91
Example of lasso regression machine learning model......Page 94
Summary......Page 96
Maximum likelihood estimation......Page 97
Logistic regression – introduction and advantages......Page 99
Terminology involved in logistic regression......Page 101
Example of logistic regression using German credit data......Page 108
Random forest......Page 125
Example of random forest using German credit data......Page 127
Grid search on random forest......Page 131
Variable importance plot......Page 134
Comparison of logistic regression with random forest......Page 136
Summary......Page 138
Chapter 4: Tree-Based Machine Learning Models......Page 139
Introducing decision tree classifiers......Page 140
Terminology used in decision trees......Page 141
Decision tree working methodology from first principles......Page 142
Comparison between logistic regression and decision trees......Page 148
Comparison of error components across various styles of models......Page 149
Remedial actions to push the model towards the ideal region......Page 150
HR attrition data example......Page 151
Decision tree classifier......Page 154
Tuning class weights in decision tree classifier......Page 157
Bagging classifier......Page 159
Random forest classifier......Page 163
Random forest classifier - grid search......Page 169
AdaBoost classifier......Page 172
Gradient boosting classifier......Page 177
Comparison between AdaBoosting versus gradient boosting......Page 180
Extreme gradient boosting - XGBoost classifier......Page 183
Ensemble of ensembles with different types of classifiers......Page 188
Ensemble of ensembles with bootstrap samples using a single type of classifier......Page 196
Summary......Page 199
Chapter 5: K-Nearest Neighbors and Naive Bayes......Page 200
KNN voter example......Page 201
Curse of dimensionality......Page 202
Curse of dimensionality with 1D, 2D, and 3D example......Page 205
KNN classifier with breast cancer Wisconsin data example......Page 208
Tuning of k-value in KNN classifier......Page 213
Naive Bayes......Page 216
Probability fundamentals......Page 217
Joint probability......Page 218
Understanding Bayes theorem with conditional probability......Page 219
Naive Bayes classification......Page 221
Laplace estimator......Page 222
Naive Bayes SMS spam classification example......Page 223
Summary......Page 233
Support vector machines working principles......Page 234
Maximum margin classifier......Page 235
Support vector classifier......Page 237
Support vector machines......Page 238
Kernel functions......Page 240
SVM multilabel classifier with letter recognition data example......Page 241
Maximum margin classifier - linear kernel......Page 242
Polynomial kernel......Page 245
RBF kernel......Page 247
Artificial neural networks - ANN......Page 254
Activation functions......Page 257
Forward propagation and backpropagation......Page 258
Optimization of neural networks......Page 267
Stochastic gradient descent - SGD......Page 268
Momentum......Page 269
Nesterov accelerated gradient - NAG......Page 270
RMSprop......Page 271
Limited-memory broyden-fletcher-goldfarb-shanno - L-BFGS optimization algorithm......Page 272
Dropout in neural networks......Page 274
ANN classifier applied on handwritten digits using scikit-learn......Page 275
Introduction to deep learning......Page 281
Solving methodology......Page 283
Deep learning software......Page 284
Deep neural network classifier applied on handwritten digits using Keras......Page 285
Summary......Page 293
Content-based filtering......Page 294
Cosine similarity......Page 295
Collaborative filtering......Page 296
Matrix factorization using the alternating least squares algorithm for collaborative filtering......Page 297
Hyperparameter selection in recommendation engines using grid search......Page 300
Recommendation engine application on movie lens data......Page 301
User-user similarity matrix......Page 304
Movie-movie similarity matrix......Page 306
Collaborative filtering using ALS......Page 308
Grid search on collaborative filtering......Page 313
Summary......Page 317
Chapter 8: Unsupervised Learning......Page 318
K-means clustering......Page 319
K-means working methodology from first principles......Page 320
The elbow method......Page 327
K-means clustering with the iris data example......Page 328
Principal component analysis - PCA......Page 334
PCA working methodology from first principles......Page 339
PCA applied on handwritten digits using scikit-learn......Page 342
Singular value decomposition - SVD......Page 353
SVD applied on handwritten digits using scikit-learn......Page 354
Deep auto encoders......Page 357
Model building technique using encoder-decoder architecture......Page 358
Deep auto encoders applied on handwritten digits using Keras......Page 360
Summary......Page 371
Chapter 9: Reinforcement Learning......Page 372
Comparing supervised, unsupervised, and reinforcement learning in detail......Page 373
Characteristics of reinforcement learning......Page 374
Reinforcement learning basics......Page 375
Category 1 - value based......Page 379
Category 4 - model-free......Page 380
Category 5 - model-based......Page 381
Markov decision processes and Bellman equations......Page 382
Dynamic programming......Page 390
Algorithms to compute optimal policy using dynamic programming......Page 391
Grid world example using value and policy iteration algorithms with basic Python......Page 395
Key advantages of MC over DP methods......Page 402
Monte Carlo prediction......Page 404
The suitability of Monte Carlo prediction on grid-world problems......Page 405
Modeling Blackjack example of Monte Carlo methods using Python......Page 406
Temporal difference learning......Page 416
TD prediction......Page 417
Driving office example for TD learning......Page 419
SARSA on-policy TD control......Page 420
Q-learning - off-policy TD control......Page 422
Cliff walking example of on-policy and off-policy of TD control......Page 423
Automotive vehicle control - self-driving cars......Page 429
Google DeepMind\'s AlphaGo......Page 430
Robo soccer......Page 431
Summary......Page 432
Index......Page 433
Index......Page 0