With the amount of published research, patents, white papers, and other written knowledge out there, it's hard to be even reasonably sure you're aware of the goings-on around a certain topic or field. Omnity is a search engine made to make it easier by extracting the gist of documents you give it and finding related ones from a library of millions -- and now supports over a hundred languages. The process is simple and free, at least for the public-facing databases Omnity has assembled, comprising U.S. patents, SEC filings, PubMed papers, clinical trials, Library of Congress collections, and more. You upload a document or text snippet, and the system scans it, looking for the least common words and phrases -- which generally indicate things like topic, experiment type, equipment used, that sort of thing. It then looks through its own libraries to find documents with similar or related phrases that appear in a manner that suggests relevance. For example, say you put in the results of your clinical trial testing a food additive on a certain strain of mice, and found it resulted in a certain condition.

Since 2006, deep learning (DL) has become a rapidly growing research direction, redefining state-of-the-art performances in a wide range of areas such as object recognition, image segmentation, speech recognition and machine translation. In modern manufacturing systems, data-driven machine health monitoring is gaining in popularity due to the widespread deployment of low-cost sensors and their connection to the Internet. Meanwhile, deep learning provides useful tools for processing and analyzing these big machinery data. The main purpose of this paper is to review and summarize the emerging research work of deep learning on machine health monitoring. After the brief introduction of deep learning techniques, the applications of deep learning in machine health monitoring systems are reviewed mainly from the following aspects: Auto-encoder (AE) and its variants, Restricted Boltzmann Machines and its variants including Deep Belief Network (DBN) and Deep Boltzmann Machines (DBM), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). Finally, some new trends of DL-based machine health monitoring methods are discussed.

Recently, sentiment analysis has received a lot of attention due to the interest in mining opinions of social media users. Sentiment analysis consists in determining the polarity of a given text, i.e., its degree of positiveness or negativeness. Traditionally, Sentiment Analysis algorithms have been tailored to a specific language given the complexity of having a number of lexical variations and errors introduced by the people generating content. In this contribution, our aim is to provide a simple to implement and easy to use multilingual framework, that can serve as a baseline for sentiment analysis contests, and as starting point to build new sentiment analysis systems. We compare our approach in eight different languages, three of them have important international contests, namely, SemEval (English), TASS (Spanish), and SENTIPOLC (Italian). Within the competitions our approach reaches from medium to high positions in the rankings; whereas in the remaining languages our approach outperforms the reported results.

Existing models based on artificial neural networks (ANNs) for sentence classification often do not incorporate the context in which sentences appear, and classify sentences individually. However, traditional sentence classification approaches have been shown to greatly benefit from jointly classifying subsequent sentences, such as with conditional random fields. In this work, we present an ANN architecture that combines the effectiveness of typical ANN models to classify sentences in isolation, with the strength of structured prediction. Our model achieves state-of-the-art results on two different datasets for sequential sentence classification in medical abstracts.

Bayesian inference is a popular method to build learning algorithms but it is hampered by the fact that its key object, the posterior probability distribution, is often uncomputable. Expectation Propagation (EP) (Minka [2001]) is a popular algorithm that solves this issue by computing a parametric approximation (e.g: Gaussian) to the density of the posterior. However, while it is known empirically to quickly compute fine approximations, EP is extremely poorly understood which prevents it from being adopted by a larger fraction of the community. The object of the present article is to shed intuitive light on EP, by relating it to other better understood methods. More precisely, we link it to using gradient descent to compute the Laplace approximation of a target probability distribution. We show that EP is exactly equivalent to performing gradient descent on a smoothed energy landscape: i.e: the original energy landscape convoluted with some smoothing kernel. This also relates EP to algorithms that compute the Gaussian approximation which minimizes the reverse KL divergence to the target distribution, a link that has been conjectured before but has not been proved rigorously yet. These results can help practitioners to get a better feel for how EP works, as well as lead to other new results on this important method. This article was submitted and accepted to the Advances in Approximate Bayesian Inference NIPS 2016 workshop (www.approximateinference.org).

Bayesian inference on structured models typically relies on the ability to infer posterior distributions of underlying hidden variables. However, inference in implicit models or complex posterior distributions is hard. A popular tool for learning implicit models are generative adversarial networks (GANs) which learn parameters of generators by fooling discriminators. Typically, GANs are considered to be models themselves and are not understood in the context of inference. Current techniques rely on inefficient global discrimination of joint distributions to perform learning, or only consider discriminating a single output variable. We overcome these limitations by treating GANs as a basis for likelihood-free inference in generative models and generalize them to Bayesian posterior inference over factor graphs. We propose local learning rules based on message passing minimizing a global divergence criterion involving cooperating local adversaries used to sidestep explicit likelihood evaluations. This allows us to compose models and yields a unified inference and learning framework for adversarial learning. Our framework treats model specification and inference separately and facilitates richly structured models within the family of Directed Acyclic Graphs, including components such as intractable likelihoods, non-differentiable models, simulators and generally cumbersome models. A key result of our treatment is the insight that Bayesian inference on structured models can be performed only with sampling and discrimination when using nonparametric variational families, without access to explicit distributions. As a side-result, we discuss the link to likelihood maximization. These approaches hold promise to be useful in the toolbox of probabilistic modelers and enrich the gamut of current probabilistic programming applications.

We address the problem of semi-supervised learning in relational networks, networks in which nodes are entities and links are the relationships or interactions between them. Typically this problem is confounded with the problem of graph-based semi-supervised learning (GSSL), because both problems represent the data as a graph and predict the missing class labels of nodes. However, not all graphs are created equally. In GSSL a graph is constructed, often from independent data, based on similarity. As such, edges tend to connect instances with the same class label. Relational networks, however, can be more heterogeneous and edges do not always indicate similarity. For instance, instead of links being more likely to connect nodes with the same class label, they may occur more frequently between nodes with different class labels (link-heterogeneity). Or nodes with the same class label do not necessarily have the same type of connectivity across the whole network (class-heterogeneity), e.g. in a network of sexual interactions we may observe links between opposite genders in some parts of the graph and links between the same genders in others. Performing classification in networks with different types of heterogeneity is a hard problem that is made harder still when we do not know a-priori the type or level of heterogeneity. Here we present two scalable approaches for graph-based semi-supervised learning for the more general case of relational networks. We demonstrate these approaches on synthetic and real-world networks that display different link patterns within and between classes. Compared to state-of-the-art approaches, ours give better classification performance without prior knowledge of how classes interact. In particular, our two-step label propagation algorithm gives consistently good accuracy and runs on networks of over 1.6 million nodes and 30 million edges in around 12 seconds.

We demonstrate the possibility of classifying causal systems into kinds that share a common structure without first constructing an explicit dynamical model or using prior knowledge of the system dynamics. The algorithmic ability to determine whether arbitrary systems are governed by causal relations of the same form offers significant practical applications in the development and validation of dynamical models. It is also of theoretical interest as an essential stage in the scientific inference of laws from empirical data. The algorithm presented is based on the dynamical symmetry approach to dynamical kinds. A dynamical symmetry with respect to time is an intervention on one or more variables of a system that commutes with the time evolution of the system. A dynamical kind is a class of systems sharing a set of dynamical symmetries. The algorithm presented classifies deterministic, time-dependent causal systems by directly comparing their exhibited symmetries. Using simulated, noisy data from a variety of nonlinear systems, we show that this algorithm correctly sorts systems into dynamical kinds. It is robust under significant sampling error, is immune to violations of normality in sampling error, and fails gracefully with increasing dynamical similarity. The algorithm we demonstrate is the first to address this aspect of automated scientific discovery.

Identifying measurable genetic indicators (or biomarkers) of a specific condition of a biological system is a key element of precision medicine. Indeed it allows to tailor diagnostic, prognostic and treatment choice to individual characteristics of a patient. In machine learning terms, biomarker discovery can be framed as a feature selection problem on whole-genome data sets. However, classical feature selection methods are usually underpowered to process these data sets, which contain orders of magnitude more features than samples. This can be addressed by making the assumption that genetic features that are linked on a biological network are more likely to work jointly towards explaining the phenotype of interest. We review here three families of methods for feature selection that integrate prior knowledge in the form of networks.

In this paper, we resolve many of the key algorithmic questions regarding robustness, memory efficiency, and differential privacy of tensor decomposition. We propose simple variants of the tensor power method which enjoy these strong properties. We present the first guarantees for online tensor power method which has a linear memory requirement. Moreover, we present a noise calibrated tensor power method with efficient privacy guarantees. At the heart of all these guarantees lies a careful perturbation analysis derived in this paper which improves up on the existing results significantly.