Recently, a clinical study led by Finnish researchers was launched in Tampere to use the latest analytical methods to recognize those myocardial infarction patients at high risk of complications. The project makes comprehensive use of data generated during treatment, but which is usually fragmented into separate systems, and complements it by continuing to monitor how the patient's heart is functioning after he or she has been discharged from hospital. The mass of data thus gathered is analysed using A.I. and machine-learning methods, which have been taught with the help of former patient-treatment data and developed to be applied to myocardial infarction patients. What the study means for the patients in practice is that a small ECG recorder is attached to their chest when they are leaving the hospital. It can also be linked to the Internet for monitoring purposes for as long as the measurements require.

This study proposes a fully convolutional network (FCN) model for raw waveform-based speech enhancement. The proposed system performs speech enhancement in an end-to-end (i.e., waveform-in and waveform-out) manner, which dif-fers from most existing denoising methods that process the magnitude spectrum (e.g., log power spectrum (LPS)) only. Because the fully connected layers, which are involved in deep neural networks (DNN) and convolutional neural networks (CNN), may not accurately characterize the local information of speech signals, particularly with high frequency components, we employed fully convolutional layers to model the waveform. More specifically, FCN consists of only convolutional layers and thus the local temporal structures of speech signals can be efficiently and effectively preserved with relatively few weights. Experimental results show that DNN- and CNN-based models have limited capability to restore high frequency components of waveforms, thus leading to decreased intelligibility of enhanced speech. By contrast, the proposed FCN model can not only effectively recover the waveforms but also outperform the LPS-based DNN baseline in terms of short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ). In addition, the number of model parameters in FCN is approximately only 0.2% compared with that in both DNN and CNN.

This paper proposes a new family of algorithms for training neural networks (NNs). These are based on recent developments in the field of non-convex optimization, going under the general name of successive convex approximation (SCA) techniques. The basic idea is to iteratively replace the original (non-convex, highly dimensional) learning problem with a sequence of (strongly convex) approximations, which are both accurate and simple to optimize. Differently from similar ideas (e.g., quasi-Newton algorithms), the approximations can be constructed using only first-order information of the neural network function, in a stochastic fashion, while exploiting the overall structure of the learning problem for a faster convergence. We discuss several use cases, based on different choices for the loss function (e.g., squared loss and cross-entropy loss), and for the regularization of the NN's weights. We experiment on several medium-sized benchmark problems, and on a large-scale dataset involving simulated physical data. The results show how the algorithm outperforms state-of-the-art techniques, providing faster convergence to a better minimum. Additionally, we show how the algorithm can be easily parallelized over multiple computational units without hindering its performance. In particular, each computational unit can optimize a tailored surrogate function defined on a randomly assigned subset of the input variables, whose dimension can be selected depending entirely on the available computational power.

Here, we present a novel approach to solve the problem of reconstructing perceived stimuli from brain responses by combining probabilistic inference with deep learning. Our approach first inverts the linear transformation from latent features to brain responses with maximum a posteriori estimation and then inverts the nonlinear transformation from perceived stimuli to latent features with adversarial training of convolutional neural networks. We test our approach with a functional magnetic resonance imaging experiment and show that it can generate state-of-the-art reconstructions of perceived faces from brain activations.

The goal of the paper is to design sequential strategies which lead to efficient optimization of an unknown function under the only assumption that it has a finite Lipschitz constant. We first identify sufficient conditions for the consistency of generic sequential algorithms and formulate the expected minimax rate for their performance. We introduce and analyze a first algorithm called LIPO which assumes the Lipschitz constant to be known. Consistency, minimax rates for LIPO are proved, as well as fast rates under an additional H\"older like condition. An adaptive version of LIPO is also introduced for the more realistic setup where the Lipschitz constant is unknown and has to be estimated along with the optimization. Similar theoretical guarantees are shown to hold for the adaptive LIPO algorithm and a numerical assessment is provided at the end of the paper to illustrate the potential of this strategy with respect to state-of-the-art methods over typical benchmark problems for global optimization.

We address the problem of learning a ranking by using adaptively chosen pairwise comparisons. Our goal is to recover the ranking accurately but to sample the comparisons sparingly. If all comparison outcomes are consistent with the ranking, the optimal solution is to use an efficient sorting algorithm, such as Quicksort. But how do sorting algorithms behave if some comparison outcomes are inconsistent with the ranking? We give favorable guarantees for Quicksort for the popular Bradley-Terry model, under natural assumptions on the parameters. Furthermore, we empirically demonstrate that sorting algorithms lead to a very simple and effective active learning strategy: repeatedly sort the items. This strategy performs as well as state-of-the-art methods (and much better than random sampling) at a minuscule fraction of the computational cost.

A host of bizarre biomedical robots turned up at ICRA 2017, IEEE's flagship robotics conference, which took place earlier this month in Singapore. We saw swallowable robots that poke the stomach with needles and worm-like robots that explore the colon. Equal parts unnerving and fascinating, these bots aim to help people--perhaps in ways we hope we never need. This capsule robot innocuously tumbles around inside your stomach--until it reaches suspicious-looking tissue. Then, like an EpiPen on steroids, the soft-bodied bot whips out a needle and jabs that spot inside your stomach in ten fast pumping movements.

Hassan Ugail is a Professor of Visual Computing and the Director of the Centre for Visual Computing at University of Bradford, UK. He works in the broad area of computer graphics, machine learning and artificial intelligence. In particular, he has developed novel computer based methods for reading and analysing the human face using artificial intelligence and machine learning techniques.

Steve sits up and takes in the crisp new daylight pouring through the bedroom window. He looks down at his companion, still pretending to sleep. She stirs out of bed and begins dressing. "You received 164 messages overnight. I answered all but one."

In the technical and largely male-dominated world of Artificial Intelligence, the notion of making emotional connections seems completely counter-intuitive…until you talk with Olga Russakovsky. As co-founder of SAILORS (Stanford Artificial Intelligence Laboratory's Outreach Summer), America's first AI summer camp for teen girls, Olga reflects on what she refers to as a "transformative experience." It was a simple moment that occurred one morning when the SAILORS camp girls were at breakfast. "Girls were sitting there, braiding each other's hair…and discussing AI!" she says. "Watching them do something so girly like braiding hair while they were talking through their research project at SAILORS was so inspiring!"