In the two months since Richard Watson strapped 200 remote-control-sized transmitters around his cows' necks, an artificial-intelligence system named Ida has pinged his phone with helpful alerts: when his cows are chewing the cud, when they're feeling sick, when they're ready for insemination. "There may be 10 animals out there that have a real problem, but could you pick them?" he said one morning, standing among a grazing herd of dairy cattle wearing what he calls "cow Fitbits." But on the neighboring pastures here in rural Georgia, other farmers say they aren't that impressed. When a cow's in heat, they know she'll start getting mounted by her bovine sisters, so they smear paint on the cows' backsides and then just look for the incriminating smudge. "I can spot a cow across a room that don't feel great just by looking in her eyes," said Mark Rodgers, a fourth-generation dairy farmer in Dearing, Georgia, whose dad still drives a tractor at 82. "The good Lord said, 'This is what you can do.' I can't draw, paint or anything else, but I can watch cows."

Spurred by the enthusiasm surrounding the "Big Data" paradigm, the mathematical and algorithmic tools of online optimization have found widespread use in problems where the trade-off between data exploration and exploitation plays a predominant role. This trade-off is of particular importance to several branches and applications of signal processing, such as data mining, statistical inference, multimedia indexing and wireless communications (to name but a few). With this in mind, the aim of this tutorial paper is to provide a gentle introduction to online optimization and learning algorithms that are asymptotically optimal in hindsight - i.e., they approach the performance of a virtual algorithm with unlimited computational power and full knowledge of the future, a property known as no-regret. Particular attention is devoted to identifying the algorithms' theoretical performance guarantees and to establish links with classic optimization paradigms (both static and stochastic). To allow a better understanding of this toolbox, we provide several examples throughout the tutorial ranging from metric learning to wireless resource allocation problems.

Decision making based on behavioral and neural observations of living systems has been extensively studied in brain science, psychology, and other disciplines. Decision-making mechanisms have also been experimentally implemented in physical processes, such as single photons and chaotic lasers. The findings of these experiments suggest that there is a certain common basis in describing decision making, regardless of its physical realizations. In this study, we propose a local reservoir model to account for choice-based learning (CBL). CBL describes decision consistency as a phenomenon where making a certain decision increases the possibility of making that same decision again later, which has been intensively investigated in neuroscience, psychology, etc. Our proposed model is inspired by the viewpoint that a decision is affected by its local environment, which is referred to as a local reservoir. If the size of the local reservoir is large enough, consecutive decision making will not be affected by previous decisions, thus showing lower degrees of decision consistency in CBL. In contrast, if the size of the local reservoir decreases, a biased distribution occurs within it, which leads to higher degrees of decision consistency in CBL. In this study, an analytical approach on local reservoirs is presented, as well as several numerical demonstrations. Furthermore, a physical architecture for CBL based on single photons is discussed, and the effects of local reservoirs is numerically demonstrated. Decision consistency in human decision-making tasks and in recruiting empirical data are evaluated based on local reservoir. In summary, the proposed local reservoir model paves a path toward establishing a foundation for computational mechanisms and the systematic analysis of decision making on different levels.

Abstract-- This paper aims to identify in a practical manner unknown physical parameters, such as mechanical models of actuated robot links, which are critical in dynamical robotic tasks. Key features include the use of an off-the-shelf physics engine and the Bayesian optimization framework. The task being considered is locomotion with a high-dimensional, compliant Tensegrity robot. A key insight, in this case, is the need to project the model identification challenge into an appropriate lower dimensional space for efficiency. Comparisons with alternatives indicate that the proposed method can identify the parameters more accurately within the given time budget, which also results in more precise locomotion control. I. INTRODUCTION This paper presents an approach for model identification by exploiting the availability of off-the-shelf physics engines used for simulating dynamics of robots and objects they interact with. There are many examples of popular physics engines that are becoming increasingly efficient [1]-[6].

Discovering the causal structure among a set of variables is a fundamental problem in many areas of science. In this paper, we propose Kernel Conditional Deviance for Causal Inference (KCDC) a fully nonparametric causal discovery method based on purely observational data. From a novel interpretation of the notion of asymmetry between cause and effect, we derive a corresponding asymmetry measure using the framework of reproducing kernel Hilbert spaces. Based on this, we propose three decision rules for causal discovery. We demonstrate the wide applicability of our method across a range of diverse synthetic datasets. Furthermore, we test our method on real-world time series data and the real-world benchmark dataset Tubingen Cause-Effect Pairs where we outperform existing state-of-the-art methods.

Affinity propagation is one of the most effective algorithms for data clustering in high-dimensional feature space. However the numerous attempts to test its performance for community detection in real complex networks have been attaining results very far from the state of the art methods such as Infomap and Louvain. Yet, all these studies agreed that the crucial problem is to convert the network topology in a 'smart-enough' dissimilarity matrix that is able to properly address the message passing procedure behind affinity propagation clustering. Here we discuss how to leverage network latent geometry notions in order to design dissimilarity matrices for affinity propagation community detection. Our results demonstrate that the dissimilarity measures we designed bring affinity propagation to outperform current state of the art methods for community detection, not only on several original real networks, but also when their structure is corrupted by noise artificially induced by missing or spurious connectivity.

Navigated 2D multi-slice dynamic Magnetic Resonance (MR) imaging enables high contrast 4D MR imaging during free breathing and provides in-vivo observations for treatment planning and guidance. Navigator slices are vital for retrospective stacking of 2D data slices in this method. However, they also prolong the acquisition sessions. Temporal interpolation of navigator slices an be used to reduce the number of navigator acquisitions without degrading specificity in stacking. In this work, we propose a convolutional neural network (CNN) based method for temporal interpolation via motion field prediction. The proposed formulation incorporates the prior knowledge that a motion field underlies changes in the image intensities over time. Previous approaches that interpolate directly in the intensity space are prone to produce blurry images or even remove structures in the images. Our method avoids such problems and faithfully preserves the information in the image. Further, an important advantage of our formulation is that it provides an unsupervised estimation of bi-directional motion fields. We show that these motion fields can be used to halve the number of registrations required during 4D reconstruction, thus substantially reducing the reconstruction time.

Convolutional Neural Networks (CNNs) require a large amount of annotated data to learn from, which is often difficult to obtain in the medical domain. In this paper we show that the sample complexity of CNNs can be significantly improved by using 3D roto-translation group convolutions (G-Convs) instead of the more conventional translational convolutions. These 3D G-CNNs were applied to the problem of false positive reduction for pulmonary nodule detection, and proved to be substantially more effective in terms of performance, sensitivity to malignant nodules, and speed of convergence compared to a strong and comparable baseline architecture with regular convolutions, data augmentation and a similar number of parameters. For every dataset size tested, the G-CNN achieved a FROC score close to the CNN trained on ten times more data.

This paper describes the participation of Amobee in the shared sentiment analysis task at SemEval 2018. We participated in all the English sub-tasks and the Spanish valence tasks. Our system consists of three parts: training task-specific word embeddings, training a model consisting of gated-recurrent-units (GRU) with a convolution neural network (CNN) attention mechanism and training stacking-based ensembles for each of the sub-tasks. Our algorithm reached 3rd and 1st places in the valence ordinal classification sub-tasks in English and Spanish, respectively.

Parameter identification and comparison of dynamical systems is a challenging task in many fields. Bayesian approaches based on Gaussian process regression over time-series data have been successfully applied to infer the parameters of a dynamical system without explicitly solving it. While the benefits in computational cost are well established, a rigorous mathematical framework has been missing. We offer a novel interpretation which leads to a better understanding and improvements in state-of-the-art performance in terms of accuracy for nonlinear dynamical systems.