Search

Label ranking is a complex prediction task where the goal is to map instances to a total order over a finite set of predefined labels. An interesting aspect of this problem is that it subsumes several supervised learning problems, such as multiclass prediction, multilabel classification, and hierarchical classification. Unsurprisingly, there exists a plethora of label ranking algorithms in the literature due, in part, to this versatile nature of the problem. In this paper, we survey these algorithms. [ABSTRACT FROM AUTHOR]

The availability of mobile devices without a keypad like Apple΄s iPad and iPhone grows continuously and the demand for sophisticated input methods with them. In this paper we present classifiers for on-line handwriting recognition based on SVM and kNN algorithms and provide a comparison of the different classifiers using the freely available handwriting corpus UjiPenchars2. We further investigate how their performance can be improved by parallelization and how these improvements can be utilized on a mobile device. [ABSTRACT FROM AUTHOR]

In this paper we rule out output polynomial listing algorithms for the general problem of discovering theories for a conjunction of monotone and anti-monotone constraints as well as for the particular subproblem in which all constraints are frequency-based. For the general problem we prove a concrete exponential lower time bound that holds for any correct algorithm and even in cases in which the size of the theory as well as the only previous bound are constant. For the case of frequency-based constraints our result holds unless P = NP. These findings motivate further research to identify tractable subproblems and justify approaches with exponential worst case complexity. [ABSTRACT FROM AUTHOR]

In this paper we aim at automatically adjusting the difficulty of computer games by clustering players into different types and supervised prediction of the type from short traces of gameplay. An important ingredient of video games is to challenge players by providing them with tasks of appropriate and increasing difficulty. How this difficulty should be chosen and increase over time strongly depends on the ability, experience, perception and learning curve of each individual player. It is a subjective parameter that is very difficult to set. Wrong choices can easily lead to players stopping to play the game as they get bored (if underburdened) or frustrated (if overburdened). An ideal game should be able to adjust its difficulty dynamically governed by the player΄s performance. Modern video games utilise a game-testing process to investigate among other factors the perceived difficulty for a multitude of players. In this paper, we investigate how machine learning techniques can be used for automatic difficulty adjustment. Our experiments confirm the potential of machine learning in this application. [ABSTRACT FROM AUTHOR]

In this work we propose to cluster image search results based on the textual contents of the referring webpages. The natural ambiguity and context-dependence of human languages lead to problems that plague modern image search engines: A user formulating a query usually has in mind just one topic, while the results produced to satisfy this query may (and usually do) belong to the different topics. Therefore, only part of the search results are relevant for a user. One of the possible ways to improve the user΄s experience is to cluster the results according to the topics they belong to and present the clustered results to the user. As opposed to the clustering based on visual features, an approach utilising the text information in the webpages containing the image is less computationally intensive and provides the resulting clusters with semantically meaningful names. [ABSTRACT FROM AUTHOR]

In this paper we investigate the problem of classifying vertices of a directed graph according to an unknown directed cut. We first consider the usual setting in which the directed cut is fixed. However, even in this setting learning is not possible without in the worst case needing the labels for the whole vertex set. By considering the size of the minimum path cover as a fixed parameter, we derive positive learnability results with tight performance guarantees for active, online, as well as PAC learning. The advantage of this parameter over possible alternatives is that it allows for an a priori estimation of the total cost of labelling all vertices. The main result of this paper is the analysis of learning directed cuts that depend on a hidden and changing context. [ABSTRACT FROM AUTHOR]

In contrast to the standard inductive inference setting of predictive machine learning, in real world learning problems often the test instances are already available at training time. Transductive inference tries to improve the predictive accuracy of learning algorithms by making use of the information contained in these test instances. Although this description of transductive inference applies to predictive learning problems in general, most transductive approaches consider the case of classification only. In this paper we introduce a transductive variant of Gaussian process regression with automatic model selection, based on approximate moment matching between training and test data. Empirical results show the feasibility and competitiveness of this approach. [ABSTRACT FROM AUTHOR]