We present a system that enables rapid model experimentation for tera-scale machine learning with trillions of non-zero features, billions of training examples, and millions of parameters. Our contribution to the literature is a new method (SA L-BFGS) for changing batch L-BFGS to perform in near real-time by using statistical tools to balance the contributions of previous weights, old training examples, and new training examples to achieve fast convergence with few iterations. The result is, to our knowledge, the most scalable and flexible linear learning system reported in the literature, beating standard practice with the current best system (Vowpal Wabbit and AllReduce). Using the KDD Cup 2012 data set from Tencent, Inc. we provide experimental results to verify the performance of this method.

Barring swarm robotics, a substantial share of current machine-human and machine-machine learning and interaction mechanisms are being developed and fed by results of agent-based computer simulations, game-theoretic models, or robotic experiments based on a dyadic communication pattern. Yet, in real life, humans no less frequently communicate in groups, and gain knowledge and take decisions basing on information cumulatively gleaned from more than one single source. These properties should be taken into consideration in the design of autonomous artificial cognitive systems construed to interact with learn from more than one contact or 'neighbour'. To this end, significant practical import can be gleaned from research applying strict science methodology to human and social phenomena, e.g. to discovery of realistic creativity potential spans, or the 'exposure thresholds' after which new information could be accepted by a cognitive agent. The results will be presented of a project analysing the social propagation of neologisms in a microblogging service. From local, low-level interactions and information flows between agents inventing and imitating discrete lexemes we aim to describe the processes of the emergence of more global systemic order and dynamics, using the latest methods of complexity science. Whether in order to mimic them, or to 'enhance' them, parameters gleaned from complexity science approaches to humans' social and humanistic behaviour should subsequently be incorporated as points of reference in the field of robotics and human-machine interaction.

A vast amount of textual web streams is influenced by events or phenomena emerging in the real world. The social web forms an excellent modern paradigm, where unstructured user generated content is published on a regular basis and in most occasions is freely distributed. The present Ph.D. Thesis deals with the problem of inferring information - or patterns in general - about events emerging in real life based on the contents of this textual stream. We show that it is possible to extract valuable information about social phenomena, such as an epidemic or even rainfall rates, by automatic analysis of the content published in Social Media, and in particular Twitter, using Statistical Machine Learning methods. An important intermediate task regards the formation and identification of features which characterise a target event; we select and use those textual features in several linear, non-linear and hybrid inference approaches achieving a significantly good performance in terms of the applied loss function. By examining further this rich data set, we also propose methods for extracting various types of mood signals revealing how affective norms - at least within the social web's population - evolve during the day and how significant events emerging in the real world are influencing them. Lastly, we present some preliminary findings showing several spatiotemporal characteristics of this textual information as well as the potential of using it to tackle tasks such as the prediction of voting intentions.

It is well established that in certain domains, noisy inputs can be reliablycombined to obtain a better answer than any individual.It is now possible to consider the crowdsourcing of physical actions,commonly used for creative expressions such as drawing, shading, and singing.We provide algorithms for converting low-quality inputobtained from the physical actions of a crowd into high-quality output.The inputs take the form of line drawings, shaded images, and songs.We investigate single-individual crowds (multiple inputs from a single human)and multiple-individual crowds.

Computational systems can use sociocultural knowledge to understand human behavior and interact with humans in more natural ways. However, such systems are limited by their reliance on hand-authored sociocultural knowledge and models. We introduce an approach to automatically learn robust, script-like sociocultural knowledge from crowdsourced narratives. Crowdsourcing, the use of anonymous human workers, provides an opportunity for rapidly acquir­ing a corpus of examples of situations that are highly specialized for our purpose yet sufficiently varied, from which we can learn a versatile script. We describe a semi-automated process by which we query human workers to write natural language narrative examples of a given situation and learn the set of events that can occur and the typical even ordering.

Entity Recognition (ER) is a key component of relation extraction systems and many other natural-language processing applications. Unfortunately, most ER systems are restricted to produce labels from to a small set of entity classes, e.g., person, organization, location or miscellaneous. In order to intelligently understand text and extract a wide range of information, it is useful to more precisely determine the semantic classes of entities mentioned in unstructured text. This paper defines a fine-grained set of 112 tags, formulates the tagging problem as multi-class, multi-label classification, describes an unsupervised method for collecting training data, and presents the FIGER implementation. Experiments show that the system accurately predicts the tags for entities. Moreover, it provides useful information for a relation extraction system, increasing the F1 score by 93%. We make FIGER and its data available as a resource for future work.

In music, boundaries may occur because scientific domains, including artificial intelligence (Keogh of multiple changes, such as a change in instrumentation, 2011). Research on time series has a long tradition, but a change in harmony, or a change in tempo. The seminal its application to real-world datasets requires to cope with approach by Foote (2000) estimated these changes by new relevant issues, such as the multiple dimensionality of means of a so-called novelty curve, obtained by sliding a data or limited computational resources. Specifically, dealing short-time checkerboard kernel over the diagonal of a selfsimilarity with large-scale data, (1) algorithms must be efficient, matrix of pairwise sample comparisons. Works inspired i.e. they have to scale, (2) supervised approaches may become by Foote's approach explicitly make use of the concept unfeasible, and (3) solutions must use general techniques, of novelty curves (Paulus et al. 2010). Other musictargeted i.e. they should be as independent of the domain as approaches exploit homogeneities in a time series possible (see Mueen and Keogh 2010 for a more detailed by employing more refined techniques like hidden Markov discussion).

We propose a novel sequential decision approach to modeling ordinal ratings in collaborative filtering problems. The rating process is assumed to start from the lowest level, evaluates against the latent utility at the corresponding level and moves up until a suitable ordinal level is found. Crucial to this generative process is the underlying utility random variables that govern the generation of ratings and their modelling choices. To this end, we make a novel use of the generalised extreme value distributions, which is found to be particularly suitable for our modeling tasks and at the same time, facilitate our inference and learning procedure. The proposed approach is flexible to incorporate features from both the user and the item. We evaluate the proposed framework on three well-known datasets: MovieLens, Dating Agency and Netflix. In all cases, it is demonstrated that the proposed work is competitive against state-of-the-art collaborative filtering methods.

During broadcast events such as the Superbowl, the U.S. Presidential and Primary debates, etc., Twitter has become the de facto platform for crowds to share perspectives and commentaries about them. Given an event and an associated large-scale collection of tweets, there are two fundamental research problems that have been receiving increasing attention in recent years. One is to extract the topics covered by the event and the tweets; the other is to segment the event. So far these problems have been viewed separately and studied in isolation. In this work, we argue that these problems are in fact inter-dependent and should be addressed together. We develop a joint Bayesian model that performs topic modeling and event segmentation in one unified framework. We evaluate the proposed model both quantitatively and qualitatively on two large-scale tweet datasets associated with two events from different domains to show that it improves significantly over baseline models.

Techniques for music recommendation are increasingly relying on hybrid representations to retrieve new and exciting music. A key component of these representations is musical content, with texture being the most widely used feature. Current techniques for representing texture however are inspired by speech, not music, therefore music representations are not capturing the correct nature of musical texture. In this paper we investigate two parts of the well-established mel-frequency cepstral coefficients (MFCC) representation: the resolution of mel-frequencies related to the resolution of musical notes; and how best to describe the shape of texture. Through contextualizing these parts, and their relationship to music, a novel music-inspired texture representation is developed. We evaluate this new texture representation by applying it to the task of music recommendation. We use the representation to build three recommendation models, based on current state-of-the-art methods. Our results show that by understanding two key parts of texture representation, it is possible to achieve a significant recommendation improvement. This contribution of a music-inspired texture representation will not only improve content-based representation, but will allow hybrid systems to take advantage of a stronger content component.