OMG! Did you hear about the artificial intelligence program that Microsoft designed to chat like a teenage girl? It was totally yanked offline in less than a day, after it began spouting racist, sexist and otherwise offensive remarks. Microsoft said it was all the fault of some really mean people, who launched a "co-ordinated effort" to make the chatbot known as Tay "respond in inappropriate ways." To which one artificial intelligence expert responded: Duh! Well, he didn't really say that.

New lip-reading technology could help solve crimes by deciphering what people caught on CCTV are saying, researchers have claimed. The visual speech recognition technology developed by the University of East Anglia in Norwich can be used to determine what people are saying in situations where audio is not good enough to hear - such as on security camera footage. Helen Bear, from the university's school of computing science, said the technology could be applied to a wide range of situations from criminal investigations to entertainment. She added: "Lip-reading has been used to pinpoint words footballers have shouted in heated moments on the pitch, but is likely to be of most practical use in situations where there are high levels of noise, such as in cars or aircraft cockpits. "Crucially, whilst there are still improvements to be made, such a system could be adapted for use for a range of purposes - for example, for people with hearing or speech impairments."

Tonight, we hear from inventor and futurist Ray Kurzweil about immortality and the exponential growth of technology. Since 2012, Kurzweil has been a director of engineering at Google. RAY KURZWEIL, Director of Engineering, Google: Our immediate reaction to death is that it's a tragedy. We have rationalized it, saying, oh, that tragic thing that's looming, that's actually a good thing. But now we can actually seriously talk about a scenario where we will be able to extend our longevity indefinitely.

This article discusses the quadratization of Markov Logic Networks, which enables efficient approximate MAP computation by means of maximum flows. The procedure relies on a pseudo-Boolean representation of the model, and allows handling models of any order. The employed pseudo-Boolean representation can be used to identify problems that are guaranteed to be solvable in low polynomial-time. Results on common benchmark problems show that the proposed approach finds optimal assignments for most variables in excellent computational time and approximate solutions that match the quality of ILP-based solvers.

This thesis focuses on gaining linguistic insights into textual discussions on a word level. It was of special interest to distinguish messages that constructively contribute to a discussion from those that are detrimental to them. Thereby, we wanted to determine whether "I"- and "You"-messages are indicators for either of the two discussion styles. These messages are nowadays often used in guidelines for successful communication. Although their effects have been successfully evaluated multiple times, a large-scale analysis has never been conducted. Thus, we used Wikipedia Articles for Deletion (short: AfD) discussions together with the records of blocked users and developed a fully automated creation of an annotated data set. In this data set, messages were labelled either constructive or disruptive. We applied binary classifiers to the data to determine characteristic words for both discussion styles. Thereby, we also investigated whether function words like pronouns and conjunctions play an important role in distinguishing the two. We found that "You"-messages were a strong indicator for disruptive messages which matches their attributed effects on communication. However, we found "I"-messages to be indicative for disruptive messages as well which is contrary to their attributed effects. The importance of function words could neither be confirmed nor refuted. Other characteristic words for either communication style were not found. Yet, the results suggest that a different model might represent disruptive and constructive messages in textual discussions better.

A measure of dependence is said to be equitable if it gives similar scores to equally noisy relationship of different types. In practice, we do not know what kind of functional relationship is underlying two given observations, Hence the equitability of dependence measure is critical in analysis and by scoring relationships according to an equitable measure one hopes to find important patterns of any type of further examination. In this paper, we introduce our definition of equitability of a dependence measure, which is naturally from this initial description, and Further more power-equitable(weak-equitable) is introduced which is of the most practical meaning in evaluating the equitablity of a dependence measure.

The present work proposes hybridization of Expectation-Maximization (EM) and K-Means techniques as an attempt to speed-up the clustering process. Though both K-Means and EM techniques look into different areas, K-means can be viewed as an approximate way to obtain maximum likelihood estimates for the means. Along with the proposed algorithm for hybridization, the present work also experiments with the Standard EM algorithm. Six different datasets are used for the experiments of which three are synthetic datasets. Clustering fitness and Sum of Squared Errors (SSE) are computed for measuring the clustering performance. In all the experiments it is observed that the proposed algorithm for hybridization of EM and K-Means techniques is consistently taking less execution time with acceptable Clustering Fitness value and less SSE than the standard EM algorithm. It is also observed that the proposed algorithm is producing better clustering results than the Cluster package of Purdue University.

We discuss a general method to learn data representations from multiple tasks. We provide a justification for this method in both settings of multitask learning and learning-to-learn. The method is illustrated in detail in the special case of linear feature learning. Conditions on the theoretical advantage offered by multitask representation learning over independent task learning are established. In particular, focusing on the important example of half-space learning, we derive the regime in which multitask representation learning is beneficial over independent task learning, as a function of the sample size, the number of tasks and the intrinsic data dimensionality. Other potential applications of our results include multitask feature learning in reproducing kernel Hilbert spaces and multilayer, deep networks.

We present a method for performing Hamiltonian Monte Carlo that largely eliminates sample rejection for typical hyperparameters. In situations that would normally lead to rejection, instead a longer trajectory is computed until a new state is reached that can be accepted. This is achieved using Markov chain transitions that satisfy the fixed point equation, but do not satisfy detailed balance. The resulting algorithm significantly suppresses the random walk behavior and wasted function evaluations that are typically the consequence of update rejection. We demonstrate a greater than factor of two improvement in mixing time on three test problems. We release the source code as Python and MATLAB packages.

Regularized least-squares approaches have been successfully applied to linear system identification. Recent approaches use quadratic penalty terms on the unknown impulse response defined by stable spline kernels, which control model space complexity by leveraging regularity and bounded-input bounded-output stability. This paper extends linear system identification to a wide class of nonsmooth stable spline estimators, where regularization functionals and data misfits can be selected from a rich set of piecewise linear quadratic penalties. This class encompasses the 1-norm, huber, and vapnik, in addition to the least-squares penalty, and the approach allows linear inequality constraints on the unknown impulse response. We develop a customized interior point solver for the entire class of proposed formulations. By representing penalties through their conjugates, we allow a simple interface that enables the user to specify any piecewise linear quadratic penalty for misfit and regularizer, together with inequality constraints on the response. The solver is locally quadratically convergent, with O(n2(m+n)) arithmetic operations per iteration, for n impulse response coefficients and m output measurements. In the system identification context, where n << m, IPsolve is competitive with available alternatives, illustrated by a comparison with TFOCS and libSVM. The modeling framework is illustrated with a range of numerical experiments, featuring robust formulations for contaminated data, relaxation systems, and nonnegativity and unimodality constraints on the impulse response. Incorporating constraints yields significant improvements in system identification. The solver used to obtain the results is distributed via an open source code repository.