Thoughtful Machine Learning by Kirk, Matthew -- Read -- Imperial Library of Trantor

Index

Preface

What to Expect from This Book How to Read This Book Who This Book Is For How to Contact Me Conventions Used in This Book Using Code Examples Safari® Books Online How to Contact Us Acknowledgments

1. Test-Driven Machine Learning

History of Test-Driven Development TDD and the Scientific Method

TDD Makes a Logical Proposition of Validity

Example: Proof through axioms and functional tests Example: Proof through sufficient conditions, unit tests, and integration tests

TDD Involves Writing Your Assumptions Down on Paper or in Code TDD and Scientific Method Work in Feedback Loops

Example: Peer review

Risks with Machine Learning

Unstable Data Underfitting Overfitting Unpredictable Future

What to Test for to Reduce Risks

Mitigate Unstable Data with Seam Testing Example: Seam testing a neural network Check Fit by Cross-Validating Example: Cross-validating a model Reduce Overfitting Risk by Testing the Speed of Training Example: Benchmark testing Monitor for Future Shifts with Precision and Recall

Conclusion

2. A Quick Introduction to Machine Learning

What Is Machine Learning?

Supervised Learning Unsupervised Learning Reinforcement Learning

What Can Machine Learning Accomplish? Mathematical Notation Used Throughout the Book Conclusion

3. K-Nearest Neighbors Classification

History of K-Nearest Neighbors Classification House Happiness Based on a Neighborhood How Do You Pick K?

Guessing K Heuristics for Picking K

Use coprime class and K combinations Choose a K that is greater or equal to the number of classes + 1 Choose a K that is low enough to avoid noise

Algorithms for Picking K

What Makes a Neighbor “Near”?

Minkowski Distance Mahalanobis Distance

Determining Classes Beard and Glasses Detection Using KNN and OpenCV

The Class Diagram Raw Image to Avatar The Face Class

Testing the Face class

The Neighborhood Class

Bootstrapping the neighborhood with faces Cross-validation and finding K

Conclusion

4. Naive Bayesian Classification

Using Bayes’ Theorem to Find Fraudulent Orders

Conditional Probabilities Inverse Conditional Probability (aka Bayes’ Theorem)

Naive Bayesian Classifier

The Chain Rule Naivety in Bayesian Reasoning Pseudocount

Spam Filter

The Class Diagram Data Source Email Class Tokenization and Context The SpamTrainer Storing training data Building the Bayesian classifier Calculating a classification Error Minimization Through Cross-Validation Minimizing false positives Building the two folds Cross-validation and error measuring

Conclusion

5. Hidden Markov Models

Tracking User Behavior Using State Machines

Emissions/Observations of Underlying States Simplification through the Markov Assumption Using Markov Chains Instead of a Finite State Machine Hidden Markov Model

Evaluation: Forward-Backward Algorithm

Using User Behavior

The Decoding Problem through the Viterbi Algorithm The Learning Problem Part-of-Speech Tagging with the Brown Corpus

The Seam of Our Part-of-Speech Tagger: CorpusParser Writing the Part-of-Speech Tagger Cross-Validating to Get Confidence in the Model How to Make This Model Better

Conclusion

6. Support Vector Machines

Solving the Loyalty Mapping Problem Derivation of SVM Nonlinear Data

The Kernel Trick Homogenous polynomial Heterogenous polynomial Radial basis functions When should you use each kernel? Soft Margins Optimizing with slack Trading off margin maximization with slack variable minimization using C

Using SVM to Determine Sentiment

The Class Diagram Corpus Class Tokenization of text Sentiment leaning, :positive or :negative Sentiment codes for :positive and :negative Return a Unique Set of Words from the Corpus The CorpusSet Class Zip two corpus objects Build a sparse vector that ties into SentimentClassifier The SentimentClassifier Class Refactoring the interaction with CorpusSet Library to handle Support Vector Machines: LibSVM Training data Cross-validating with the movie review data Improving Results Over Time

Conclusion

7. Neural Networks

History of Neural Networks What Is an Artificial Neural Network?

Input Layer

Standard inputs Symmetric inputs

Hidden Layers Neurons

Activation functions

Output Layer Training Algorithms

The delta rule Back Propagation QuickProp RProp

Building Neural Networks

How Many Hidden Layers? How Many Neurons for Each Layer? Tolerance for Error and Max Epochs

Using a Neural Network to Classify a Language

Writing the Seam Test for Language Cross-Validating Our Way to a Network Class Tuning the Neural Network Convergence Testing Precision and Recall for Neural Networks Wrap-Up of Example

Conclusion

8. Clustering

User Cohorts K-Means Clustering

The K-Means Algorithm The Downside of K-Means Clustering

Expectation Maximization (EM) Clustering The Impossibility Theorem Categorizing Music

Gathering the Data Analyzing the Data with K-Means EM Clustering EM Jazz Clustering Results

Conclusion

9. Kernel Ridge Regression

Collaborative Filtering Linear Regression Applied to Collaborative Filtering Introducing Regularization, or Ridge Regression Kernel Ridge Regression Wrap-Up of Theory Collaborative Filtering with Beer Styles

Data Set The Tools We Will Need Reviewer Writing the Code to Figure Out Someone’s Preference Collaborative Filtering with User Preferences

Conclusion

10. Improving Models and Data Extraction

The Problem with the Curse of Dimensionality Feature Selection Feature Transformation Principal Component Analysis (PCA) Independent Component Analysis (ICA) Monitoring Machine Learning Algorithms

Precision and Recall: Spam Filter The Confusion Matrix

Mean Squared Error The Wilds of Production Environments Conclusion

11. Putting It All Together

Machine Learning Algorithms Revisited How to Use This Information for Solving Problems What’s Next for You?

Index

← Prev
Back
Next →

← Prev
Back
Next →