The last ten years have seen a research explosion in machine learning. The rapid growing is largely driven by the following two forces. First, separate research communities in symbolic machine learning, computational learning theory, neural network, statistics and pattern recognition have discovered one another and begun to work together. Second, machine learning technologies are being applied ...

One of the most exciting recent directions in machine learning is the discovery that the combination of multiple classifiers often results in significantly better performance than what can be achieved with a single classifier. In this paper, we first show that the errors made from three different state of the art part of speech taggers are strongly complementary. Next, we show how this compleme...

In the so-called pairwise approach to polychotomous classification, a multi-class problem is solved by combining classifiers trained to discriminate between each pair of classes. In this paper, this approach is revisited in the framework of the Dempster-Shafer theory of belief functions, a non-probabilistic framework for quantifying and manipulating partial knowledge. It is proposed to interpre...

This paper examines the applicability of classifier combination approaches such as bagging and boosting for coreference resolution. To the best of our knowledge, this is the first effort that utilizes such techniques for coreference resolution. In this paper, we provide experimental evidence which indicates that the accuracy of the coreference engine can potentially be increased by use of baggi...

A multiple classifier system is a powerful solution to difficult pattern recognition problems involving large class sets and noisy input because it allows simultaneous use of arbitrary feature descriptors and classification procedures. Decisions by the classifiers can be represented as rankings of classes so that they are comparable across different types of classifiers and different instances ...

Although some image features and algorithms succeed in many tasks such as scene recognition and face recognition, carefully choosing image features and classifiers are time consuming for a specific image classification task. In this paper, we propose a method that automatically combines the classifiers with probability outputs from different features. We fomulate the problem in quadric programm...

Network intrusion detection is a problem that’s hardly being solved completely. Firewalls and other existing solutions do provide some resistance to the wide variety of attack types that can occur, but they suffer the drawback of not being able to generalize well into unseen attack types. Through this report, we propose a framework for addressing the problem of network intrusion by extracting i...

The combination of classifiers from independent observation domains has a myriad of benefits in practical pattern recognition problems. In this paper we propose a firm theoretical framework from which an upper bound on classifier combination performance can be calculated, based on mismatches between train and test sets. Using this framework, insights can be gained into the conditions under whic...

At its heart, music information retrieval is characterized by the need to find the similarity between pieces of music. However, “similar” does not mean “the same”. Therefore, techniques for approximate matching are crucial to the development of good music information retrieval systems. Yet as one increases the level of approximation, one finds not only additional similar, relevant music, but al...

One of the most exciting recent directions in machine learning is the discovery that the combination of multiple classifiers often results in significantly better performance than what can be achieved with a single classifier. In this paper, we first show that the errors made from three different state of the art part of speech taggers are strongly complementary. Next, we show how this compleme...