An Algorithm for Designing a Pattern Classifier by Using MDL Criterion

Hideaki TSUCHIYA  Shuichi ITOH  Takeshi HASHIMOTO  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E79-A   No.6   pp.910-920
Publication Date: 1996/06/25
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Algorithms and Data Structures
classifier,  noiseless coding,  MDL criterion,  binary tree structure,  context gathering,  

Full Text: PDF(798.4KB)>>
Buy this Article

A algorithm for designing a pattern classifier, which uses MDL criterion and a binary data structure, is proposed. The algorithm gives a partitioning of the range of the multi-dimensional attribute and gives an estimated probability model for this partitioning. The volume of bins in this partitioning is upper bounded by ο((log N/N)K/(K+2)) almost surely, where N is the length of training sequence and K is the dimension of the attribute. The convergence rates of the code length and the divergence of the estimated model are asymptotically upper bounded by ο((log N/N)2/(K+2)). The classification error is asymptotically upper bounded by ο((log N/N)1/(K+2)). Simulation results for 1-dimensional and 2-dimensional attribute cases show that the algorithm is practically efficient.