Classiier Combining: Analytical Results and Implications
نویسندگان
چکیده
Several researchers have experimentally shown that substantial improvements can be obtained in diicult pattern recognition problems by combining or integrating the outputs of multiple classiiers. This paper summarizes our recent theoretical results that quantify the improvements due to multiple classiier combining. Furthermore, we present an extension of this theory that leads to an estimate of the Bayes error rate. Practical aspects such as expressing the con-dences in decisions and determining the best data partition/classiier selection are also discussed.
منابع مشابه
Theoretical Foundations of Linear and Order Statistics Combiners for Neural Pattern Classifiers
Several researchers have experimentally shown that substantial improvements can be obtained in diicult pattern recognition problems by combining or integrating the outputs of multiple classiiers. This paper provides an analytical framework to quantify the improvements in classiication results due to combining. The results apply to both linear combiners and the order statistics combiners introdu...
متن کاملClassiier Combining through Trimmed Means and Order Statistics
| Combining the outputs of multiple neural networks has led to substantial improvements in several dii-cult pattern recognition problems. In this article, we introduce and investigate robust combiners, a family of classiiers based on order statistics. We focus our study to the analysis of the decision boundaries, and how these boundaries are aaected by order statistics combiners. In particular,...
متن کاملCombining Nearest Neighbor Classi ers Through Multiple
Combining multiple classiiers is an eeective technique for improving accuracy. There are many general combining algorithms, such as Bagging or Error Correcting Output Coding, that signiicantly improve classiiers like decision trees, rule learners, or neural networks. Unfortunately, many combining methods do not improve the nearest neighbor classiier. In this paper, we present MFS, a combining a...
متن کاملAdaptive Selection Of Image Classi
Recently, the concept of \Multiple Classiier Systems" was proposed as a new approach to the development of high performance image classiication systems. Multiple Classiier Systems can be used to improve classiication accuracy by combining the outputs of classiiers making \uncorrelated" errors. Unfortunately, in real image recognition problems, it may be very diicult to design an ensemble of cla...
متن کاملBoundary Variance Reduction for Improved Classi cation through Hybrid Networks
Several researchers have experimentally shown that substantial improvements can be obtained in diicult pattern recognition problems by combining or integrating the outputs of multiple classiiers. This paper provides an analytical framework that quantiies the improvements in classiication results due to linear combining. We show that combining networks in output space reduces the variance of the...
متن کامل