• 
  • Weitere Informationen zu diesem Buch:

    Inhaltsverzeichnis | Index | Probekapitel | Kolophon | Rezensionen |
    Beispiele |

	

Preface 
1. Introduction to Collective Intelligence

      What Is Collective Intelligence? 

      What Is Machine Learning? 

      Limits of Machine Learning 

      Real-Life Examples 

      Other Uses for Learning Algorithms 
2. Making Recommendations

      Collaborative Filtering 

      Collecting Preferences 

      Finding Similar Users 

      Recommending Items 

      Matching Products 

      Building a del.icio.us Link Recommender 

      Item-Based Filtering 

      Using the MovieLens Dataset 

      User-Based or Item-Based Filtering? 

      Exercises 
3. Discovering Groups

      Supervised versus Unsupervised Learning 

      Word Vectors 

      Hierarchical Clustering 

      Drawing the Dendrogram 

      Column Clustering 

      K-Means Clustering 

      Clusters of Preferences 

      Viewing Data in Two Dimensions 

      Other Things to Cluster 

      Exercises 
4. Searching and Ranking

      What's in a Search Engine? 

      A Simple Crawler 

      Building the Index 

      Querying 

      Content-Based Ranking 

      Using Inbound Links 

      Learning from Clicks 

      Exercises 
5. Optimization

      Group Travel 

      Representing Solutions 

      The Cost Function 

      Random Searching 

      Hill Climbing 

      Simulated Annealing 

      Genetic Algorithms 

      Real Flight Searches 

      Optimizing for Preferences 

      Network Visualization 

      Other Possibilities 

      Exercises 
6. Document Filtering

      Filtering Spam 

      Documents and Words 

      Training the Classifier 

      Calculating Probabilities 

      A Naïve Classifier 

      The Fisher Method 

      Persisting the Trained Classifiers 

      Filtering Blog Feeds 

      Improving Feature Detection 

      Using Akismet 

      Alternative Methods 

      Exercises 
7. Modeling with Decision Trees

      Predicting Signups 

      Introducing Decision Trees 

      Training the Tree 

      Choosing the Best Split 

      Recursive Tree Building 

      Displaying the Tree 

      Classifying New Observations 

      Pruning the Tree 

      Dealing with Missing Data 

      Dealing with Numerical Outcomes 

      Modeling Home Prices 

      Modeling "Hotness" 

      When to Use Decision Trees 

      Exercises 
8. Building Price Models

      Building a Sample Dataset 

      k-Nearest Neighbors 

      Weighted Neighbors 

      Cross-Validation 

      Heterogeneous Variables 

      Optimizing the Scale 

      Uneven Distributions 

      Using Real Data-the eBay API 

      When to Use k-Nearest Neighbors 

      Exercises 
9. Advanced Classification: Kernel Methods and SVMs

      Matchmaker Dataset 

      Difficulties with the Data 

      Basic Linear Classification 

      Categorical Features 

      Scaling the Data 

      Understanding Kernel Methods 

      Support-Vector Machines 

      Using LIBSVM 

      Matching on Facebook 

      Exercises 
10. Finding Independent Features

      A Corpus of News 

      Previous Approaches 

      Non-Negative Matrix Factorization 

      Displaying the Results 

      Using Stock Market Data 

      Exercises 
11. Evolving Intelligence

      What Is Genetic Programming? 

      Programs As Trees 

      Creating the Initial Population 

      Testing a Solution 

      Mutating Programs 

      Crossover 

      Building the Environment 

      A Simple Game 

      Further Possibilities 

      Exercises 
12. Algorithm Summary

      Bayesian Classifier 

      Decision Tree Classifier 

      Neural Networks 

      Support-Vector Machines 

      k-Nearest Neighbors 

      Clustering 

      Multidimensional Scaling 

      Non-Negative Matrix Factorization 

      Optimization 
A. Third-Party Libraries
B. Mathematical Formulas
Index