A Familiartiy-Based Bound on the Expected Error Rate for Classification with the Fuzzy ARTMAP Neural Network
OA Version
Citation
Abstract
We obtain a bound on the expected error rate of the fuzzy ARTMAP neural network employed as a classifier. This bound is based on leave-one-out estimation of the classification error, and is analogous to a bound on the expected error rate for support vector machines.
Description
License
Copyright 1999 Boston University. Permission to copy without fee all or part of this material is granted provided that: 1. The copies are not made or distributed for direct commercial advantage; 2. the report title, author, document number, and release date appear, and notice is given that copying is by permission of BOSTON UNIVERSITY TRUSTEES. To copy otherwise, or to republish, requires a fee and / or special permission.