This paper introduces the concept of online "Semantic Advertising", which we see as the technology that will help realize the full potential of Internet advertising. Internet advertising is a rapidly growing and arguably a dominant form of advertising. A recent IDC report (Weide, 2013) estimates that the total Internet advertising spend in 2011 was 87.4 billion dollars ($35B for the U.S. only), and predicts an annual growth rate of 16% over the next 5 years. We argue that Semantic Advertising, (SA), enables us to address the challenge of delivering relevance at scale in Internet Advertising. Our argument is based on our work as a company developing semantic technology for better online advertising. Semantic technology (Hitzler, Krotzsch and Rudolph, 2009) can be described as algorithms and software that enable representation and reasoning based on meaning. Several companies such as Google, Microsoft and Yahoo, and smaller startup companies have developed semantic technologies for advertising.

Cognitive radio networks (CRNs) are networks of nodes equipped with cognitive radios that can optimize performance by adapting to network conditions. While cognitive radio networks (CRN) are envisioned as intelligent networks, relatively little research has focused on the network level functionality of CRNs. Although various routing protocols, incorporating varying degrees of adaptiveness, have been proposed for CRNs, it is imperative for the long term success of CRNs that the design of cognitive routing protocols be pursued by the research community. Cognitive routing protocols are envisioned as routing protocols that fully and seamless incorporate AI-based techniques into their design. In this paper, we provide a self-contained tutorial on various AI and machine-learning techniques that have been, or can be, used for developing cognitive routing protocols. We also survey the application of various classes of AI techniques to CRNs in general, and to the problem of routing in particular. We discuss various decision making techniques and learning techniques from AI and document their current and potential applications to the problem of routing in CRNs. We also highlight the various inference, reasoning, modeling, and learning sub tasks that a cognitive routing protocol must solve. Finally, open research issues and future directions of work are identified.

The Classification Literature Automated Search Service, an annual bibliography based on citation of one or more of a set of around 80 book or journal publications, ran from 1972 to 2012. We analyze here the years 1994 to 2011. The Classification Society's Service, as it was termed, has been produced by the Classification Society. In earlier decades it was distributed as a diskette or CD with the Journal of Classification. Among our findings are the following: an enormous increase in scholarly production post approximately 2000; a very major increase in quantity, coupled with work in different disciplines, from approximately 2004; and a major shift also from cluster analysis in earlier times having mathematics and psychology as disciplines of the journals published in, and affiliations of authors, contrasted with, in more recent times, a "centre of gravity" in management and engineering.

Mobile manipulation robots are envisioned to provide many useful services both in domestic environments as well as in the industrial context.  In this paper, we present novel approaches to allow mobile maniplation systems to autonomously adapt to new or changing situations. The approaches developed in this paper cover the following four topics: (1) learning the robot's kinematic structure and properties using actuation and visual feedback, (2) learning about articulated objects in the environment in which the robot is operating, (3) using tactile feedback to augment visual perception, and (4) learning novel manipulation tasks from human demonstrations.

The crucial importance of metrics in machine learning algorithms has led to an increasing interest in optimizing distance and similarity functions, an area of research known as metric learning. When data consist of feature vectors, a large body of work has focused on learning a Mahalanobis distance. Less work has been devoted to metric learning from structured objects (such as strings or trees), most of it focusing on optimizing a notion of edit distance. We identify two important limitations of current metric learning approaches. First, they allow to improve the performance of local algorithms such as k-nearest neighbors, but metric learning for global algorithms (such as linear classifiers) has not been studied so far. Second, the question of the generalization ability of metric learning methods has been largely ignored. In this thesis, we propose theoretical and algorithmic contributions that address these limitations. Our first contribution is the derivation of a new kernel function built from learned edit probabilities. Our second contribution is a novel framework for learning string and tree edit similarities inspired by the recent theory of (e,g,t)-good similarity functions. Using uniform stability arguments, we establish theoretical guarantees for the learned similarity that give a bound on the generalization error of a linear classifier built from that similarity. In our third contribution, we extend these ideas to metric learning from feature vectors by proposing a bilinear similarity learning method that efficiently optimizes the (e,g,t)-goodness. Generalization guarantees are derived for our approach, highlighting that our method minimizes a tighter bound on the generalization error of the classifier. Our last contribution is a framework for establishing generalization bounds for a large class of existing metric learning algorithms based on a notion of algorithmic robustness.

When considering the problem of unmixing hyperspectral images, most of the literature in the geoscience and image processing areas relies on the widely used linear mixing model (LMM). However, the LMM may be not valid and other nonlinear models need to be considered, for instance, when there are multi-scattering effects or intimate interactions. Consequently, over the last few years, several significant contributions have been proposed to overcome the limitations inherent in the LMM. In this paper, we present an overview of recent advances in nonlinear unmixing modeling.

The digitalization of music and the instant availability of millions of tracks on the Internet require new approaches to support the user in the exploration of these huge music collections. One possible approach to address this problem, which can also be found on popular online music platforms, is the use of user-created or automatically generated playlists (mixes). The automated generation of such playlists represents a particular type of the music recommendation problem with two special characteristics. First, the tracks of the list are usually consumed immediately at recommendation time; secondly, songs are listened to mostly in consecutive order so that the sequence of the recommended tracks can be relevant. In the past years, a number of different approaches for playlist generation have been proposed in the literature. In this paper, we review the existing core approaches to playlist generation, discuss aspects of appropriate offline evaluation designs and report the results of a comparative evaluation based on different datasets. Based on the insights from these experiments, we propose a comparably simple and computationally tractable new baseline algorithm for future comparisons, which is based on track popularity and artist information and is competitive with more sophisticated techniques in our evaluation settings.

My work aims to create a scaffold for deployable intelligent systems using crowdsourcing. Current approaches in artificial intelligence (AI) typically focus on solving a narrow subset of problems in a given space - for example: automatic speech recognition as part of a conversational assistant, machine vision as part of a question answering service for blind people, or planning as part of a home assistive robot. This approach is necessary to scope the solution, but often results in a large number of systems that are rarely deployed in real-world setting, but instead operate in toy domains, or in situations where other parts of the problem are assumed to be solved. The framework I have developed aims to use the crowd to help in two ways: (i) make it possible to use human intelligence to power parts of a system that automated approaches cannot or do not yet handle, and (ii) provide a means of enabling more effective deployable systems by people to provide reliable training data on-demand. This summary begins with a brief review of prior work, then outlines a number of different system that I have developed to demonstrate the capabilities of this framework, and concludes with future work to be completed as part of my thesis.

Collusion is the practice of two or more parties deliberately cooperating to the detriment of others. While such behavior may be desirable in certain circumstances, in many it is considered dishonest and unfair. If agents otherwise hold strictly to the established rules, though, collusion can be challenging to police. In this paper, we introduce an automatic method for collusion detection in sequential games. We achieve this through a novel object, called a collusion table, that captures the effects of collusive behavior, i.e., advantage to the colluding parties, without assuming any particular pattern of behavior. We show the effectiveness of this method in the domain of poker, a popular game where collusion is prohibited.

Declarative logic programs (LP) based on the well-founded semantics (WFS) are widely used for knowledge representation (KR).  Logical functions are desirable expressively in KR, but when present make LP inferencing become undecidable. In this paper, we present radial restraint : a novel approach to bounded rationality in LP. Radial restraint is parameterized by a norm that measures the syntactic complexity of a term, along with an abstraction function based on that norm.  When a term exceeds a bound for the norm, the term is assigned the WFS's third truth-value of undefined .  If the norm is finitary, radial restraint guarantees finiteness of models and decidability of inferencing, even when logical functions are present.  It further guarantees soundness, even when non-monotonicity is present.  We give a fixed-point semantics for radially restrained well-founded models which soundly approximate well-founded models.  We also show how to perform correct inferencing relative to such models, via SLG_ABS, an extension of tabled SLG resolution that uses norm-based abstraction functions.  Finally we discuss how SLG_ABS is implemented in the engine of XSB Prolog, and scales to knowledge bases with more than 10^8 rules and facts.