Beyond Independence: Conditions for the Optimality of the Simple Bayesian Classifier
Explore this paper's citation graph
Summary
It is shown that the simple Bayesian classi er (SBC) does not in fact assume attribute independence, and can be optimal even when this assumption is violated by a wide margin, and the previously-assumed region of optimality is a second-order in nitesimal fraction of the actual one.
- Type
- article
- Published
- 1996-01-01
- Cited by
- 907
- References
- 12
- OpenAlex
- https://openalex.org/W1507029541
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:7413266
Keywords
Computer science, Bayesian probability, Artificial intelligence, Simple (philosophy), Independence (probability theory)
References
- Wrappers for performance enhancement and oblivious decision graphs
- Pattern classification and scene analysis
- UCI Repository of machine learning databases
- C4.5: Programs for Machine Learning
- UCI Repository of Machine Learning Databases
- Induction of Selective Bayesian Classifiers
- Induction of Recursive Bayesian Classifiers
- Supervised and Unsupervised Discretization of Continuous Features
- Towards a Better Understanding of Memory-based Reasoning Systems
- Rule Induction with CN2: Some Recent Improvements
- Semi-Naive Bayesian Classifier
Cited by
- Learning to rank by maximizing the AUC with linear programming for problems with binary output
- Integrating Lexical Knowledge in Learning-Based Text Categorization
- CALI: An Online Scribble Recognizer for Calligraphic Interfaces
- ROSETTA Technical Reference Manual
- A Fast Decision Tree Learning Algorithm
- Profiler-2000: Attacking the Insider Threat
- A tool to support the identification of suspect cases of exotic diseases in cattle.
- Machine Learning for Natural Language Processing
- An Implementation of Pan-So-Ri Classification Program Using Naive Bayesian Classifier
- Classification of Churn,Upselling and Appetency for KDD Cup 2009
- DutchParl. The Parliamentary Documents in Dutch
- Using genetic feature selection for improving cyber attack detection rate
- Revising User Profiles: The Search for Interesting Web Sites
- A Heuristic Lazy Bayesian Rule Algorithm
- Meeting user information needs in recommender systems
- On learning hierarchical classifications
- Averaged One-Dependence Estimators: Preliminary Results
- Pool-Based Active Learning for Text Classification
- State Space Reduction For Hierarchical Reinforcement Learning
- Data Mining for Direct Marketing: Problems and Solutions
Related papers
- Induction of Decision Trees
- On the Optimality of the Simple Bayesian Classifier under Zero-One Loss
- C4.5: Programs for Machine Learning
- UCI Repository of machine learning databases
- Bayesian Network Classifiers
- A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection
- An Analysis of Bayesian Classifiers
- Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning