This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Capacity and Error Estimates for Boolean Classifiers with Limited Complexity
April 1979 (vol. 1 no. 4)
pp. 350-356
Judea Pearl, SENIOR MEMBER, IEEE, School of Engineering and Applied Science, University of California, Los Angeles, CA 90024.
This paper extends the notions of capacity and distribution-free error estimation to nonlinear Boolean classifiers on patterns with binary-valued features. We establish quantitative relationships between the dimensionality of the feature vectors (d), the combinational complexity of the decision rule (c), the number of samples in the training set (n), and the classification performance of the resulting classifier. Our results state that the discriminating capacity of Boolean classifiers is given by the product dc, and the probability of ambiguous generalization is asymptotically given by (n/dc 1)-i 0(1Og d)/d) for large d, and n = O(dc). In addition we show that if a fraction v of the training samples is misclassified then the probability of error (r) in subsequent samples satisfies P(17r - vl > e) : 2.773 exp (dc - e2n/8) for all distributions, regardless of how the classifier was discovered.
Citation:
Judea Pearl, "Capacity and Error Estimates for Boolean Classifiers with Limited Complexity," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 1, no. 4, pp. 350-356, April 1979, doi:10.1109/TPAMI.1979.4766943
Usage of this product signifies your acceptance of the Terms of Use.