Large margin classifiers, such as the support vector machine (SVM) [1] and the maximum entropy discrimination (MED) classifier [2], have enjoyed great popularity in the signal processing and machine learning communities due to their broad applicability, robust performance, and the availability of fast software implementations. When the training data is representative of the test data, the performance of MED/SVM has theoretical guarantees that have been validated in practice [1], [3], [4]. Moreover, since the decision boundary of the MED/SVM is solely defined by a few support vectors, the algorithm can tolerate random feature distortions and perturbations. However, in many real applications, anomalous measurements are inherent to the data set due to strong environmental noise or possible sensor failures. Such anomalies arise in industrial process monitoring, video surveillance, tactical multimodal sensing, robust spectrum sensing [5], [6], and, more generally, any application that involves unattended sensors in difficult environments (Figure 1).

We develop a class of rules spanning the range between quadratic discriminant analysis and naive Bayes, through a path of sparse graphical models. A group lasso penalty is used to introduce shrinkage and encourage a similar pattern of sparsity across precision matrices. It gives sparse estimates of interactions and produces interpretable models. Inspired by the connected-components structure of the estimated precision matrices, we propose the community Bayes model, which partitions features into several conditional independent communities and splits the classification problem into separate smaller ones. The community Bayes idea is quite general and can be applied to non-Gaussian data and likelihood-based classifiers.

We investigate metric learning in the context of dynamic time warping (DTW), the by far most popular dissimilarity measure used for the comparison and analysis of motion capture data. While metric learning enables a problem-adapted representation of data, the majority of meth- ods has been proposed for vectorial data only. In this contribution, we extend the popular principle offered by the large margin nearest neighbours learner (LMNN) to DTW by treating the resulting component-wise dissimilarity values as features. We demonstrate, that this principle greatly enhances the classification accuracy in several benchmarks. Further, we show that recent auxiliary concepts such as metric regularisation can be transferred from the vectorial case to component-wise DTW in a similar way. We illustrate, that metric regularisation constitutes a crucial prerequisite for the interpretation of the resulting relevance profiles.

We propose a novel stacked generalization (stacking) method as a dynamic ensemble technique using a pool of heterogeneous classifiers for node label classification on networks. The proposed method assigns component models a set of functional coefficients, which can vary smoothly with certain topological features of a node. Compared to the traditional stacking model, the proposed method can dynamically adjust the weights of individual models as we move across the graph and provide a more versatile and significantly more accurate stacking model for label prediction on a network. We demonstrate the benefits of the proposed model using both a simulation study and real data analysis.

Machine learning is a fashionable buzzword right now in infosec, and is often referenced as the key to next-gen, signature-less security. But along with all of the hype and buzz, there also is a mind-blowing amount of misunderstanding surrounding machine learning in infosec. Machine learning isn't a silver bullet for all information security problems, and in fact can be detrimental if misinterpreted. For example, company X claims to block 99% of all malware, or company Y's intrusion detection will stop 99% of all attacks, yet customers see an overwhelming number of false positives. What do the accuracy numbers really mean? In fact, these simple statistics lose meaning without the proper context.

Multilingual Text Classification (MLTC) is a text classification task in which documents are written each in one among a set L of natural languages, and in which all documents must be classified under the same classification scheme, irrespective of language. There are two main variants of MLTC, namely Cross-Lingual Text Classification (CLTC) and Polylingual Text Classification (PLTC). In PLTC, which is the focus of this paper, we assume (differently from CLTC) that for each language in L there is a representative set of training documents; PLTC consists of improving the accuracy of each of the |L| monolingual classifiers by also leveraging the training documents written in the other (|L| − 1) languages. The obvious solution, consisting of generating a single polylingual classifier from the juxtaposed monolingual vector spaces, is usually infeasible, since the dimensionality of the resulting vector space is roughly |L| times that of a monolingual one, and is thus often unmanageable. As a response, the use of machine translation tools or multilingual dictionaries has been proposed. However, these resources are not always available, or are not always free to use. One machine-translation-free and dictionary-free method that, to the best of our knowledge, has never been applied to PLTC before, is Random Indexing (RI). We analyse RI in terms of space and time efficiency, and propose a particular configuration of it (that we dub Lightweight Random Indexing LRI). By running experiments on two well known public benchmarks, Reuters RCV1/RCV2 (a comparable corpus) and JRC-Acquis (a parallel one), we show LRI to outperform (both in terms of effectiveness and efficiency) a number of previously proposed machine-translation-free and dictionary-free PLTC methods that we use as baselines.

We propose a novel kernel based post selection inference (PSI) algorithm, which can not only handle non-linearity in data but also structured output such as multi-dimensional and multi-label outputs. Specifically, we develop a PSI algorithm for independence measures, and propose the Hilbert-Schmidt Independence Criterion (HSIC) based PSI algorithm (hsicInf). The novelty of the proposed algorithm is that it can handle non-linearity and/or structured data through kernels. Namely, the proposed algorithm can be used for wider range of applications including nonlinear multi-class classification and multi-variate regressions, while existing PSI algorithms cannot handle them. Through synthetic experiments, we show that the proposed approach can find a set of statistically significant features for both regression and classification problems. Moreover, we apply the hsicInf algorithm to a real-world data, and show that hsicInf can successfully identify important features.

Billions of connected devices, zetabytes of data, power and brand loyalty now in the hands of the consumer, businesses having to market and sell to each and every one of us. How can any business make sense of it all? How can they learn and avoid making the same mistakes – and become smarter. Oh – and did I mention much of this needs to happen in real time? That's where Machine Leaning as part of a cognitive strategy comes in to its own.

A formal branch of artificial intelligence, machine-learning builds systems that learn directly from the data they are fed and effectively program themselves to analyse that data and make accurate predictions. Having already helped multiple business sectors create new models and drive competitive advantage, now it's the turn of the insurance industry. So just how is machine-learning changing the way insurers do business? "It gives insurers three distinct advantages," explains Max Richter, managing director in Accenture's UK insurance analytics group. "The first is to mine greater volumes of data, the second to scale analytics across the organisation by working smarter and faster, and lastly by answering more complex questions from'will this customer leave me at renewal?' to'what can I do about it?'" As such it is quickly becoming an essential tool for the insurance sector, specifically enabling companies to yield higher predictive accuracy as it can fit more flexible and complex models.

Results of preclinical studies by investigators at the Medical University of South Carolina (MUSC) reported in the August 2016 issue of Arthritis & Rheumatology demonstrate for the first time that including novel biomarkers in lupus nephritis (LN) prognostic models significantly increases their power to predict therapeutic efficacy. Identifying biomarker models with sufficient predictive power is a critical step toward developing clinical decision-making tools that can rapidly identify patients who require a change in therapy and potentially reduce onset of renal fibrosis during induction therapy. Approximately half of all patients with systemic lupus erythematosus (SLE) develop LN, an immune complex-mediated glomerulonephritis. Lupus nephritis, in turn, leads to renal failure in up to 50% of patients within five years. American College of Rheumatology guidelines recommend changing LN treatment after six months of induction therapy if response to therapy is not achieved.