Each year in the United States, more than 40,000 people die by suicide, and from 1999 to 2014, the suicide rate increased 24 percent. You might think that after generations of theories and data, we would be close to understanding how to prevent self-harm, or at least predict it. But a new study concludes that the science of suicide prediction is dismal, and the established warning signs about as accurate as tea leaves. There is, however, some hope. New research shows that machine-learning algorithms can dramatically improve our predictive abilities on suicides.

Music follows a set of patterns that can extract feelings from its listeners and provoke emotional responses. While machines can now make music too, they don't give much consideration to the emotional response of their audience. But now a team of researchers has developed a machine-learning device that can detect the emotional state of listeners and make new songs that provoke new feelings. In the study, participants listened to music while wearing wireless headphones that contained brain wave sensors. The team of researchers, under the support of Osaka University's Center of Innovation (COI) program, developed the AI that detects users' brain state and provides a means for activating it through music.

Context: One of the black arts of data mining is learning the magic parameters which control the learners. In software analytics, at least for defect prediction, several methods, like grid search and differential evolution (DE), have been proposed to learn these parameters, which has been proved to be able to improve the performance scores of learners. Objective: We want to evaluate which method can find better parameters in terms of performance score and runtime cost. Methods: This paper compares grid search to differential evolution, which is an evolutionary algorithm that makes extensive use of stochastic jumps around the search space. Results: We find that the seemingly complete approach of grid search does no better, and sometimes worse, than the stochastic search. When repeated 20 times to check for conclusion validity, DE was over 210 times faster than grid search to tune Random Forests on 17 testing data sets with F-Measure Conclusions: These results are puzzling: why does a quick partial search be just as effective as a much slower, and much more, extensive search? To answer that question, we turned to the theoretical optimization literature. Bergstra and Bengio conjecture that grid search is not more effective than more randomized searchers if the underlying search space is inherently low dimensional. This is significant since recent results show that defect prediction exhibits very low intrinsic dimensionality-- an observation that explains why a fast method like DE may work as well as a seemingly more thorough grid search. This suggests, as a future research direction, that it might be possible to peek at data sets before doing any optimization in order to match the optimization algorithm to the problem at hand.

Non-linear kernel methods can be approximated by fast linear ones using suitable explicit feature maps allowing their application to large scale problems. To this end, explicit feature maps of kernels for vectorial data have been extensively studied. As many real-world data is structured, various kernels for complex data like graphs have been proposed. Indeed, many of them directly compute feature maps. However, the kernel trick is employed when the number of features is very large or the individual vertices of graphs are annotated by real-valued attributes. Can we still compute explicit feature maps efficiently under these circumstances? Triggered by this question, we investigate how general convolution kernels are composed from base kernels and construct corresponding feature maps. We apply our results to widely used graph kernels and analyze for which kernels and graph properties computation by explicit feature maps is feasible and actually more efficient. In particular, we derive feature maps for random walk and subgraph matching kernels and apply them to real-world graphs with discrete labels. Thereby, our theoretical results are confirmed experimentally by observing a phase transition when comparing running time with respect to label diversity, walk lengths and subgraph size, respectively. Moreover, we derive approximative, explicit feature maps for state-of-the-art kernels supporting real-valued attributes including the GraphHopper and Graph Invariant kernels. In extensive experiments we show that our approaches often achieve a classification accuracy close to the exact methods based on the kernel trick, but require only a fraction of their running time.

A framework is presented for unsupervised learning of representations based on infomax principle for large-scale neural populations. We use an asymptotic approximation to the Shannon's mutual information for a large neural population to demonstrate that a good initial approximation to the global information-theoretic optimum can be obtained by a hierarchical infomax method. Starting from the initial solution, an efficient algorithm based on gradient descent of the final objective function is proposed to learn representations from the input datasets, and the method works for complete, overcomplete, and undercomplete bases. As confirmed by numerical experiments, our method is robust and highly efficient for extracting salient features from input datasets. Compared with the main existing methods, our algorithm has a distinct advantage in both the training speed and the robustness of unsupervised representation learning. Furthermore, the proposed method is easily extended to the supervised or unsupervised model for training deep structure networks.

UTOMATED segmentation of skin lesions in dermoscopy images is currently a challenging problem [1]. This paper proposes an innovative method to address this problem developed by the authors. It has been structured as follows. Firstly, in this introduction, on the one hand the segmentation problem is described and, on the other, the evaluation criteria used (image database, ground truths and metrics) are shown. Secondly, the system design is presented. Thirdly, the results and the discussion are shown. A. Problems with segmentation of skin lesions in dermoscopy images Automated segmentation of a skin lesion is a complex issue, as the possible casuistry that can appear in the images is very diverse. The main problems that can de found in the image which make segmentation difficult are as follows: 1. Presence of hair; 2. Other artifacts such as electronic letters, rulers, ink and color charts, etc.; 3. Dark rectangular or circular marks around it (a consequence of shadow); 4. Flashes; 5. Lighting problems: apart from the problem with dark marks and flashes that have already been mentioned, in some cases one part of the image turns out to be darker than another (a common cases is that the part of the skin beside the circular marks is often darker as it is less brightly lit, and some images also turn out to be darker than others; 6. As a result of the oil used to acquire many images, there may be distortion problems and bubbles; 7. Presence of blood vessels; 8. Presence of regression areas and blue-whitish veil -in many cases these structures have greater intensity than the skin surrounding the lesion; 9. Hypopigmentation areas which are confused with skin; 10.

As companies increase their efforts in retaining customers, being able to predict accurately ahead of time, whether a customer will churn in the foreseeable future is an extremely powerful tool for any marketing team. The paper describes in depth the application of Deep Learning in the problem of churn prediction. Using abstract feature vectors, that can generated on any subscription based company's user event logs, the paper proves that through the use of the intrinsic property of Deep Neural Networks (learning secondary features in an unsupervised manner), the complete pipeline can be applied to any subscription based company with extremely good churn predictive performance. Furthermore the research documented in the paper was performed for Framed Data (a company that sells churn prediction as a service for other companies) in conjunction with the Data Science Institute at Lancaster University, UK. This paper is the intellectual property of Framed Data.

Feature extraction and dimension reduction for networks is critical in a wide variety of domains. Efficiently and accurately learning features for multiple graphs has important applications in statistical inference on graphs. We propose a method to jointly embed multiple undirected graphs. Given a set of graphs, the joint embedding method identifies a linear subspace spanned by rank one symmetric matrices and projects adjacency matrices of graphs into this subspace. The projection coefficients can be treated as features of the graphs. We also propose a random graph model which generalizes classical random graph model and can be used to model multiple graphs. We show through theory and numerical experiments that under the model, the joint embedding method produces estimates of parameters with small errors. Via simulation experiments, we demonstrate that the joint embedding method produces features which lead to state of the art performance in classifying graphs. Applying the joint embedding method to human brain graphs, we find it extract interpretable features that can be used to predict individual composite creativity index.

The time to converge to the steady state of a finite Markov chain can be greatly reduced by a lifting operation, which creates a new Markov chain on an expanded state space. For a class of quadratic objectives, we show an analogous behavior where a distributed ADMM algorithm can be seen as a lifting of Gradient Descent algorithm. This provides a deep insight for its faster convergence rate under optimal parameter tuning. We conjecture that this gain is always present, as opposed to the lifting of a Markov chain which sometimes only provides a marginal speedup.

High signal to noise ratio (SNR) consistency of model selection criteria in linear regression models has attracted a lot of attention recently. However, most of the existing literature on high SNR consistency deals with model order selection. Further, the limited literature available on the high SNR consistency of subset selection procedures (SSPs) is applicable to linear regression with full rank measurement matrices only. Hence, the performance of SSPs used in underdetermined linear models (a.k.a compressive sensing (CS) algorithms) at high SNR is largely unknown. This paper fills this gap by deriving necessary and sufficient conditions for the high SNR consistency of popular CS algorithms like $l_0$-minimization, basis pursuit de-noising or LASSO, orthogonal matching pursuit and Dantzig selector. Necessary conditions analytically establish the high SNR inconsistency of CS algorithms when used with the tuning parameters discussed in literature. Novel tuning parameters with SNR adaptations are developed using the sufficient conditions and the choice of SNR adaptations are discussed analytically using convergence rate analysis. CS algorithms with the proposed tuning parameters are numerically shown to be high SNR consistent and outperform existing tuning parameters in the moderate to high SNR regime.