In this paper we present anaverage-case analysis of the Bayesian classifier, a simple induction algorithm that fares remarkably well on many learning tasks. Our analysis assumes a monotone conjunctive target concept, and independent, noise-free Boolean attributes. We calculate the probability that the algorithm will induce an arbitrary pair of concept descriptions and then use this to compute the probability of correct classification over the instance space. The analysis takes into account the number of training instances, the number of attributes, the distribution of these attributes, and the level of class noise. We also explore the behavioral implications of the analysis by presenting

When modeling a probability distribution with a Bayesian network, we are faced with the problem of how to handle continuous variables. Most previous work has either solved the problem by discretizing, or assumed that the data are generated by a single Gaussian. In this paper we abandon the normality assumption and instead use statistical methods for nonparametric density estimation. For a naive Bayesian classifier, we present experimental results on a variety of natural and artificial domains, comparing two methods of density estimation: assuming normality and modeling each conditional distribution with a single Gaussian; and using nonparametric kernel density estimation. We observe large reductions in error on several natural and artificial data sets, which suggests that kernel estimation is a useful tool for learning Bayesian models. In Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann Publishers, San Mateo, 1995 1 Introduction In rec...

... mining time series data. Literally hundreds of papers have introduced new algorithms to index, classify, cluster and segment time series. In this work we make the following claim. Much of this work has very little utility because the contribution made (speed in the case of indexing, accuracy in the case of classification and clustering, model accuracy in the case of segmentation) offer an amount of "improvement" that would have been completely dwarfed by the variance that would have been observed by testing on many real world datasets, or the variance that would have been observed by changing minor (unstated) implementation details. To illustrate our point

Abstract. An important component of many data mining projects is finding a good classification algorithm, a process that requires very careful thought about experimental design. If not done very carefully, comparative studies of classification and other types of algorithms can easily result in statistically invalid conclusions. This is especially true when one is using data mining techniques to analyze very large databases, which inevitably contain some statistically unlikely data. This paper describes several phenomena that can, if ignored, invalidate an experimental comparison. These phenomena and the conclusions that follow apply not only to classification, but to computational experiments in almost any aspect of data mining. The paper also discusses why comparative analysis is more important in evaluating some types of algorithms than for others, and provides some suggestions about how to avoid the pitfalls suffered by many experimental studies.

Most empirical evaluations of machine learning algorithms are case studies -- evaluations of multiple algorithms on multiple databases. Authors of case studies implicitly or explicitly hypothesize that the pattern of their results, which often suggests that one algorithm performs significantly better than others, is not limited to the small number of databases investigated, but instead holds for some general class of learning problems. However, these hypotheses are rarely supported with additional evidence, which leaves them suspect. This paper describes an empirical method for generalizing results from case studies and an example application. This method yields rules describing when some algorithms significantly outperform others on some dependent measures. Advantages for generalizing from case studies and limitations of this particular approach are also described. 1 PROBLEM AND OBJECTIVES A central objective in machine learning research is to determine the conditions describing when...

An important area of application for machine learning is in automating the acquisition of knowledge bases required for expert systems. In this paper, we review the major paradigms for machine learning, including neural networks, instance-based methods, genetic learning, rule induction, and analytic approaches. We consider rule induction in greater detail and review some of its recent applications, in each case stating the problem, how rule induction was used, and the status of the resulting expert system. In closing, we identify the main stages in fielding an applied learning system and draw some lessons from successful applications. Introduction Machine learning is the study of computational methods for improving performance by mechanizing the acquisition of knowledge from experience. Expert performance requires much domainspecific knowledge, and knowledge engineering has produced hundreds of AI expert systems that are now used regularly in industry. Machine learning aims to provide ...

To Mom, Dad, and Susan, for their support and encouragement.

A neural-network ensemble is a very successful technique where the outputs of a set of separately trained neural network are combined to form one unified prediction. An effective ensemble should consist of a set of networks that are not only highly correct, but ones that make their errors on different parts of the input space as well; however, most existing techniques only indirectly address the problem of creating such a set. We present an algorithm called Addemup that uses genetic algorithms to explicitly search for a highly diverse set of accurate trained networks. Addemup works by first creating an initial population, then uses genetic operators to continually create new networks, keeping the set of networks that are highly accurate while disagreeing with each other as much as possible. Experiments on four real-world domains show that Addemup is able to generate a set of trained networks that is more accurate than several existing ensemble approaches. Experiments also show that Ad...

Tree induction and logistic regression are two standard, off-the-shelf methods for building models for classi cation. We present a large-scale experimental comparison of logistic regression and tree induction, assessing classification accuracy and the quality of rankings based on class-membership probabilities. We use a learning-curve analysis to examine the relationship of these measures to the size of the training set. The results of the study show several remarkable things. (1) Contrary to prior observations, logistic regression does not generally outperform tree induction. (2) More specifically, and not surprisingly, logistic regression is better for smaller training sets and tree induction for larger data sets. Importantly, this often holds for training sets drawn from the same domain (i.e., the learning curves cross), so conclusions about induction-algorithm superiority on a given domain must be based on an analysis of the learning curves. (3) Contrary to conventional wisdom, tree induction is effective atproducing probability-based rankings, although apparently comparatively less so foragiven training{set size than at making classifications. Finally, (4) the domains on which tree induction and logistic regression are ultimately preferable canbecharacterized surprisingly well by a simple measure of signal-to-noise ratio.

Case-based reasoning systems have traditionally been used to perform high-level reasoning in problem domains that can be adequately described using discrete, symbolic representations. However, many real-world problem domains, such as autonomous robotic navigation, are better characterized using continuous representations. Such problem domains also require continuous performance, such as online sensorimotor interaction with the environment, and continuous adaptation and learning during the performance task. This article introduces a new method for continuous case-based reasoning, and discusses its application to the dynamic selection, modification, and acquisition of robot behaviors in an autonomous navigation system, SINS (Self-Improving Navigation System). The computer program and the underlying method are systematically evaluated through statistical analysis of results from several empirical studies. The article concludes with a general discussion of case-based reasoning issues addr...