Twenty years later that link is firmly established, and the two research communities have largely merged into one. Problem," by Steve Hanks and Drew Mc-or does not hold after a sequence of learning was the "inductive bias" of a The idea is this: Normally, an object learn the target concept--the more in 1986, helped initiate a very constraining the inductive bias, the is unaffected by an action. If a window fruitful integration of a branch of machine less training data needed. Starting in the of PAC learning was being developed, an action. There are clear exceptions, 1950s, with work like Samuels's program which allowed deriving quantitative however, such as the act of closing the that learned strategies for playing bounds on the probability of window. A variety of formal systems checkers, AI researchers had designed successful learning as a function of the have been proposed that would allow and experimented with a number of training examples and the us to infer in the absence of conflicting variety of learning algorithms and complexity of the learner's hypothesis information that the window remains had also developed a number of theoretical space (as measured by its Vapnik-open (or that a polar bear is results, such as convergence Chervonenkis dimension). What white or that a violin has four strings, proofs for perceptrons and "learning Haussler's paper did was help introduce and so on).

XML, web services, and the semantic web have opened the door for new and exciting informationintegration applications. Information sources on the web are controlled by different organizations or people, utilize different text formats, and have varying inconsistencies. Therefore, any system that integrates information from different data sources must identify common entities from these sources. Data from many data sources on the web does not contain enough information to link the records accurately using state-of-the-art record-linkage systems. However, it is possible to exploit secondary data sources on the web to improve the recordlinkage process. We present an approach to accurately and automatically match entities from various data sources by utilizing a state-of-the-art record-linkage system in conjunction with a data-integration system. The data-integration system is able to automatically determine which secondary sources need to be queried when linking records from various data sources. In turn, the record-linkage system is then able to utilize this additional information to improve the accuracy of the linkage between datasets.

In this paper we concentrate on the resolution of the lexical ambiguity that arises when a given word has several different meanings. This specific task is commonly referred to as word sense disambiguation (WSD). The task of WSD consists of assigning the correct sense to words using an electronic dictionary as the source of word definitions. We present two WSD methods based on two main methodological approaches in this research area: a knowledge-based method and a corpus-based method. Our hypothesis is that word-sense disambiguation requires several knowledge sources in order to solve the semantic ambiguity of the words. These sources can be of different kinds--- for example, syntagmatic, paradigmatic or statistical information. Our approach combines various sources of knowledge, through combinations of the two WSD methods mentioned above. Mainly, the paper concentrates on how to combine these methods and sources of information in order to achieve good results in the disambiguation. Finally, this paper presents a comprehensive study and experimental work on evaluation of the methods and their combinations.

There has been increased interest in devising learning techniques that combine unlabeled data with labeled data - i.e. semi-supervised learning. However, to the best of our knowledge, no study has been performed across various techniques and different types and amounts of labeled and unlabeled data. Moreover, most of the published work on semi-supervised learning techniques assumes that the labeled and unlabeled data come from the same distribution. It is possible for the labeling process to be associated with a selection bias such that the distributions of data points in the labeled and unlabeled sets are different. Not correcting for such bias can result in biased function approximation with potentially poor performance. In this paper, we present an empirical study of various semi-supervised learning techniques on a variety of datasets. We attempt to answer various questions such as the effect of independence or relevance amongst features, the effect of the size of the labeled and unlabeled sets and the effect of noise. We also investigate the impact of sample-selection bias on the semi -supervised learning techniques under study and implement a bivariate probit technique particularly designed to correct for such bias.

Mutual Boosting is a method aimed at incorporating contextual information to augment object detection. When multiple detectors of objects and parts are trained in parallel using AdaBoost [1], object detectors might use the remaining intermediate detectors to enrich the weak learner set. This method generalizes the efficient features suggested by Viola and Jones [2] thus enabling information inference between parts and objects in a compositional hierarchy. In our experiments eye-, nose-, mouth-and face detectors are trained using the Mutual Boosting framework. Results show that the method outperforms applications overlooking contextual information. We suggest that achieving contextual integration is a step toward humanlike detection capabilities.

At a cocktail party, a listener can selectively attend to a single voice and filter out other acoustical interferences. How to simulate this perceptual ability remains a great challenge. This paper describes a novel supervised learning approach to speech segregation, in which a target speech signal is separated from interfering sounds using spatial location cues: interaural time differences (ITD) and interaural intensity differences (IID). Motivated by the auditory masking effect, we employ the notion of an ideal time-frequency binary mask, which selects the target if it is stronger than the interference in a local time-frequency unit. Within a narrow frequency band, modifications to the relative strength of the target source with respect to the interference trigger systematic changes for estimated ITD and IID.

Although discriminatively trained classifiers are usually more accurate when labeled training data is abundant, previous work has shown that when training data is limited, generative classifiers can outperform them. This paper describes a hybrid model in which a high-dimensional subset of the parameters are trained to maximize generative likelihood, and another, small, subset of parameters are discriminatively trained to maximize conditional likelihood. We give a sample complexity bound showing that in order to fit the discriminative parameters well, the number of training examples required depends only on the logarithm of the number of feature occurrences and feature set size. Experimental results show that hybrid models can provide lower test error and can produce better accuracy/coverage curves than either their purely generative or purely discriminative counterparts. We also discuss several advantages of hybrid models, and advocate further work in this area.

Label ranking is the task of inferring a total order over a predefined set of labels for each given instance. We present a general framework for batch learning of label ranking functions from supervised data. We assume that each instance in the training data is associated with a list of preferences over the label-set, however we do not assume that this list is either complete or consistent. This enables us to accommodate a variety of ranking problems. In contrast to the general form of the supervision, our goal is to learn a ranking function that induces a total order over the entire set of labels. Special cases of our setting are multilabel categorization and hierarchical classification. We present a general boosting-based learning algorithm for the label ranking problem and prove a lower bound on the progress of each boosting iteration. The applicability of our approach is demonstrated with a set of experiments on a large-scale text corpus.

The Minimax Probability Machine Classification (MPMC) framework [Lanckriet et al., 2002] builds classifiers by minimizing the maximum probability of misclassification, and gives direct estimates of the probabilistic accuracy bound Ω. The only assumptions that MPMC makes is that good estimates of means and covariance matrices of the classes exist. However, as with Support Vector Machines, MPMC is computationally expensive and requires extensive cross validation experiments to choose kernels and kernel parameters that give good performance. In this paper we address the computational cost of MPMC by proposing an algorithm that constructs nonlinear sparse MPMC (SMPMC) models by incrementally adding basis functions (i.e.

Learning from ambiguous training data is highly relevant in many applications. We present a new learning algorithm for classification problems where labels are associated with sets of pattern instead of individual patterns. This encompasses multiple instance learning as a special case. Our approach is based on a generalization of linear programming boosting and uses results from disjunctive programming to generate successively stronger linear relaxations of a discrete non-convex problem.