Regular medical records are useful for medical practitioners to analyze and monitor patient's health status especially for those with chronic disease, but such records are usually incomplete due to unpunctuality and absence of patients. In order to resolve the missing data problem over time, tensorbased model is suggested for missing data imputation in recent papers because this approach makes use of low rank tensor assumption for highly correlated data. However, when the time intervals between records are long, the data correlation is not high along temporal direction and such assumption is not valid. To address this problem, we propose to decompose a matrix with missing data into its latent factors. Then, the locally linear constraint is imposed on these factors for matrix completion in this paper. By using a publicly available dataset and two medical datasets collected from hospital, experimental results show that the proposed algorithm achieves the best performance by comparing with the existing methods.

Recurrent neural networks are powerful models for processing sequential data, but they are generally plagued by vanishing and exploding gradient problems. Unitary recurrent neural networks (uRNNs), which use unitary recurrence matrices, have recently been proposed as a means to avoid these issues. However, in previous experiments, the recurrence matrices were restricted to be a product of parameterized unitary matrices, and an open question remains: when does such a parameterization fail to represent all unitary matrices, and how does this restricted representational capacity limit what can be learned? To address this question, we propose full-capacity uRNNs that optimize their recurrence matrix over all unitary matrices, leading to significantly improved performance over uRNNs that use a restricted-capacity recurrence matrix. Our contribution consists of two main components. First, we provide a theoretical argument to determine if a unitary parameterization has restricted capacity. Using this argument, we show that a recently proposed unitary parameterization has restricted capacity for hidden state dimension greater than 7. Second, we show how a complete, full-capacity unitary recurrence matrix can be optimized over the differentiable manifold of unitary matrices. The resulting multiplicative gradient step is very simple and does not require gradient clipping or learning rate adaptation. We confirm the utility of our claims by empirically evaluating our new full-capacity uRNNs on both synthetic and natural data, achieving superior performance compared to both LSTMs and the original restricted-capacity uRNNs.

Abstract--Usually, complex-valued RKHS are presented as an straightforward application of the real-valued case. In this paper we prove that this procedure yields a limited solution for regression. We show that another kernel, here denoted as pseudo-kernel, is needed to learn any function in complex-valued fields. Accordingly, we derive a novel RKHS to include it, the widely RKHS (WRKHS). When the pseudo-kernel cancels, WRKHS reduces to complex-valued RKHS of previous approaches. We address the kernel and pseudo-kernel design, paying attention to the kernel and the pseudo-kernel being complex-valued. In the experiments included we report remarkable improvements in simple scenarios where real a imaginary parts have different similitude relations for given inputs or cases where real and imaginary parts are correlated. In the context of these novel results we revisit the problem of nonlinear channel equalization, to show that the WRKHS helps to design more efficient solutions. OMPLEX-V ALUED signal processing is of fundamental interest. Its main benefit is the availability of processing the real and imaginary parts as a single signal.

We study active learning where the labeler can not only return incorrect labels but also abstain from labeling. We consider different noise and abstention conditions of the labeler. We propose an algorithm which utilizes abstention responses, and analyze its statistical consistency and query complexity under fairly natural assumptions on the noise and abstention rate of the labeler. This algorithm is adaptive in a sense that it can automatically request less queries with a more informed or less noisy labeler. We couple our algorithm with lower bounds to show that under some technical conditions, it achieves nearly optimal query complexity.

Patient notes contain a wealth of information of potentially great interest to medical investigators. However, to protect patients' privacy, Protected Health Information (PHI) must be removed from the patient notes before they can be legally released, a process known as patient note de-identification. The main objective for a de-identification system is to have the highest possible recall. Recently, the first neural-network-based de-identification system has been proposed, yielding state-of-the-art results. Unlike other systems, it does not rely on human-engineered features, which allows it to be quickly deployed, but does not leverage knowledge from human experts or from electronic health records (EHRs). In this work, we explore a method to incorporate human-engineered features as well as features derived from EHRs to a neural-network-based de-identification system. Our results show that the addition of features, especially the EHR-derived features, further improves the state-of-the-art in patient note de-identification, including for some of the most sensitive PHI types such as patient names. Since in a real-life setting patient notes typically come with EHRs, we recommend developers of de-identification systems to leverage the information EHRs contain.

We propose a methodology to explore and measure the pairwise correlations that exist between variables in a dataset. The methodology leverages copulas for encoding dependence between two variables, state-of-the-art optimal transport for providing a relevant geometry to the copulas, and clustering for summarizing the main dependence patterns found between the variables. Some of the clusters centers can be used to parameterize a novel dependence coefficient which can target or forget specific dependence patterns. Finally, we illustrate and benchmark the methodology on several datasets. Code and numerical experiments are available online for reproducible research.

Extracting actionable intelligence from distributed, heterogeneous, correlated and high-dimensional data sources requires run-time processing and learning both locally and globally. In the last decade, a large number of meta-learning techniques have been proposed in which local learners make online predictions based on their locally-collected data instances, and feed these predictions to an ensemble learner, which fuses them and issues a global prediction. However, most of these works do not provide performance guarantees or, when they do, these guarantees are asymptotic. None of these existing works provide confidence estimates about the issued predictions or rate of learning guarantees for the ensemble learner. In this paper, we provide a systematic ensemble learning method called Hedged Bandits, which comes with both long run (asymptotic) and short run (rate of learning) performance guarantees. Moreover, our approach yields performance guarantees with respect to the optimal local prediction strategy, and is also able to adapt its predictions in a data-driven manner. We illustrate the performance of Hedged Bandits in the context of medical informatics and show that it outperforms numerous online and offline ensemble learning methods.

Biological and social systems consist of myriad interacting units. The interactions can be represented in the form of a graph or network. Measurements of these graphs can reveal the underlying structure of these interactions, which provides insight into the systems that generated the graphs. Moreover, in applications such as connectomics, social networks, and genomics, graph data are accompanied by contextualizing measures on each node. We utilize these node covariates to help uncover latent communities in a graph, using a modification of spectral clustering. Statistical guarantees are provided under a joint mixture model that we call the node-contextualized stochastic blockmodel, including a bound on the mis-clustering rate. The bound is used to derive conditions for achieving perfect clustering. For most simulated cases, covariate-assisted spectral clustering yields results superior to regularized spectral clustering without node covariates and to an adaptation of canonical correlation analysis. We apply our clustering method to large brain graphs derived from diffusion MRI data, using the node locations or neurological region membership as covariates. In both cases, covariate-assisted spectral clustering yields clusters that are easier to interpret neurologically.

Researchers from the Google Brain deep learning project have already taught AI systems to make trippy works of art, but now they're moving on to something potentially darker: AI-generated, human-independent encryption. According to a new research paper, Googlers Martín Abadi and David G. Andersen have willingly allowed three test subjects -- neural networks named Alice, Bob and Eve -- to pass each other notes using an encryption method they created themselves. As the New Scientist reports, Abadi and Andersen assigned each AI a task: Alice had to send a secret message that only Bob could read, while Eve would try to figure out how to eavesdrop and decode the message herself. The experiment started with a plain-text message that Alice converted into unreadable gibberish, which Bob could decode using cipher key. At first, Alice and Bob were apparently bad at hiding their secrets, but over the course of 15,000 attempts Alice worked out her own encryption strategy and Bob simultaneously figured out how to decrypt it.

Microsoft this week released an updated version of its Microsoft Cognitive Toolkit as an open source Beta. The deep learning system is used to speed advances in areas such as speech and image recognition and search relevance on CPUs and Nvidia GPUs. It also works with Microsoft's Azure GPU offering. The Microsoft computer scientists who developed the toolkit initially were looking for a tool to speed up and improve their own research. Initially called "Microsoft/CNTK," it morphed into an offering that Microsoft customers and flagship product groups depend on for a wide variety of deep learning tasks, the company said.