One of the challenges in model-based control of stochastic dynamical systems is that the state transition dynamics are involved, and it is not easy or efficient to make good-quality predictions of the states. Moreover, there are not many representational models for the majority of autonomous systems, as it is not easy to build a compact model that captures the entire dynamical subtleties and uncertainties. In this work, we present a hierarchical Bayesian linear regression model with local features to learn the dynamics of a micro-robotic system as well as two simpler examples, consisting of a stochastic mass-spring damper and a stochastic double inverted pendulum on a cart. The model is hierarchical since we assume non-stationary priors for the model parameters. These non-stationary priors make the model more flexible by imposing priors on the priors of the model. To solve the maximum likelihood (ML) problem for this hierarchical model, we use the variational expectation maximization (EM) algorithm, and enhance the procedure by introducing hidden target variables. The algorithm yields parsimonious model structures, and consistently provides fast and accurate predictions for all our examples involving large training and test sets. This demonstrates the effectiveness of the method in learning stochastic dynamics, which makes it suitable for future use in a paradigm, such as model-based reinforcement learning, to compute optimal control policies in real time.

We consider the classical stochastic multi-armed bandit but where, from time to time and roughly with frequency $\epsilon$, an extra observation is gathered by the agent for free. We prove that, no matter how small $\epsilon$ is the agent can ensure a regret uniformly bounded in time. More precisely, we construct an algorithm with a regret smaller than $\sum_i \frac{\log(1/\epsilon)}{\Delta_i}$, up to multiplicative constant and loglog terms. We also prove a matching lower-bound, stating that no reasonable algorithm can outperform this quantity.

Motivation:Computational methods that predict differential gene expression from histone modification signals are highly desirable for understanding how histone modifications control the functional heterogeneity of cells through influencing differential gene regulation. Recent studies either failed to capture combinatorial effects on differential prediction or primarily only focused on cell type-specific analysis. In this paper we develop a novel attention-based deep learning architecture, DeepDiff, that provides a unified and end-to-end solution to model and to interpret how dependencies among histone modifications control the differential patterns of gene regulation. DeepDiff uses a hierarchy of multiple Long short-term memory (LSTM) modules to encode the spatial structure of input signals and to model how various histone modifications cooperate automatically. We introduce and train two levels of attention jointly with the target prediction, enabling DeepDiff to attend differentially to relevant modifications and to locate important genome positions for each modification. Additionally, DeepDiff introduces a novel deep-learning based multi-task formulation to use the cell-type-specific gene expression predictions as auxiliary tasks, encouraging richer feature embeddings in our primary task of differential expression prediction. Results: Using data from Roadmap Epigenomics Project (REMC) for ten different pairs of cell types, we show that DeepDiff significantly outperforms the state-of-the-art baselines for differential gene expression prediction. The learned attention weights are validated by observations from previous studies about how epigenetic mechanisms connect to differential gene expression. Availability: Codes and results are available at deepchrome.org Contact: yanjun@virginia.edu

Latent factor models for recommender systems represent users and items as low dimensional vectors. Privacy risks have been previously studied mostly in the context of recovery of personal information in the form of usage records from the training data. However, the user representations themselves may be used together with external data to recover private user information such as gender and age. In this paper we show that user vectors calculated by a common recommender system can be exploited in this way. We propose the privacy-adversarial framework to eliminate such leakage, and study the trade-off between recommender performance and leakage both theoretically and empirically using a benchmark dataset. We briefly discuss further applications of this method towards the generation of deeper and more insightful recommendations.

Despite the improved accuracy of deep neural networks, the discovery of adversarial examples has raised serious safety concerns. In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversarial example, and the feature robustness problem, which aims to quantify the robustness of individual features to adversarial perturbations. We demonstrate that, under the assumption of Lipschitz continuity, both problems can be approximated using finite optimisation by discretising the input space, and the approximation has provable guarantees, i.e., the error is bounded. We then show that the resulting optimisation problems can be reduced to the solution of two-player turn-based games, where the first player selects features and the second perturbs the image within the feature. While the second player aims to minimise the distance to an adversarial example, depending on the optimisation objective the first player can be cooperative or competitive. We employ an anytime approach to solve the games, in the sense of approximating the value of a game by monotonically improving its upper and lower bounds. The Monte Carlo tree search algorithm is applied to compute upper bounds for both games, and the Admissible A* and the Alpha-Beta Pruning algorithms are, respectively, used to compute lower bounds for the maximum safety radius and feature robustness games. When working on the upper bound of the maximum safe radius problem, our tool demonstrates competitive performance against existing adversarial example crafting algorithms. Furthermore, we show how our framework can be deployed to evaluate pointwise robustness of neural networks in safety-critical applications such as traffic sign recognition in self-driving cars.

This paper proposes an approach to detect emotion from human speech employing majority voting technique over several machine learning techniques. The contribution of this work is in two folds: firstly it selects those features of speech which is most promising for classification and secondly it uses the majority voting technique that selects the exact class of emotion. Here, majority voting technique has been applied over Neural Network (NN), Decision Tree (DT), Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). Input vector of NN, DT, SVM and KNN consists of various acoustic and prosodic features like Pitch, Mel-Frequency Cepstral coefficients etc. From speech signal many feature have been extracted and only promising features have been selected. To consider a feature as promising, Fast Correlation based feature selection (FCBF) and Fisher score algorithms have been used and only those features are selected which are highly ranked by both of them. The proposed approach has been tested on Berlin dataset of emotional speech [3] and Electromagnetic Articulography (EMA) dataset [4]. The experimental result shows that majority voting technique attains better accuracy over individual machine learning techniques. The employment of the proposed approach can effectively recognize the emotion of human beings in case of social robot, intelligent chat client, call-center of a company etc.

Waymo is ready for a dramatic next step after eight years of preparation, most of it as the Google Self-Driving Car project. The Alphabet Inc. unit has begun testing autonomous vehicles on public roads without human safety drivers at the wheel, and early next year will make its robotic chauffeurs available to Phoenix-area commuters. Speaking at the Web Summit conference in Lisbon, Portugal, Waymo CEO John Krafcik said on Tuesday that company technicians are already hailing its Chrysler Pacifica Hybrid minivans in and around Phoenix via a mobile app and leaving it to the artificial intelligence operating the vehicles to figure out how to get to requested destinations. Within a few months, Waymo vans loaded with laser LiDAR, radar, cameras, computers, AI and no human safety drivers will pick up Arizonans registered in its "Early Riders" program. People will get to use our fleet of on-demand vehicles to do anything from commute to work, get home from a night out, or run errands," Krafcik said. "Getting access will be as easy as using an app; just tap a button and Waymo will come to you, and take you where you want to go." Google's push to perfect driverless cars, stretching back to 2009, ignited a tech race in the auto industry that represents the biggest change in personal transportation since horses were replaced with horseless carriages more than a century ago. But Waymo has to move fast to lock in its early-mover status as autonomous vehicle programs at dozens of companies, ranging from General Motors to BMW to Uber to Tesla to Baidu, race to catch up and commercialize their own driverless tech. The Alphabet company appears to be first to operate an autonomous fleet without safety drivers, a transition that keeps it ahead of fast-moving rivals, at least for now. "We recently surveyed 3,000 adults across the United States, asking them when they expected to see self-driving vehicles – ones without a person in the driver's seat – on their roads.

In 2018, the Official Championships Poster celebrates the 150th anniversary of The All England Lawn Tennis Club (AELTC). The Club was founded in 1868 with the first Championships being held in 1877. The earliest poster in the Museum's collection date from 1893 – a railway poster advertising how to get to The Championships. Over the years, the Official Championships Poster has featured a range of styles, designers and world-famous artists. With such a rich heritage and a significant milestone to commemorate, the selection of an image for the 2018 poster proved to be an interesting challenge.

Football (popularly know as soccer in USA) as a sport has always been the center of attraction and excitement among the sports lovers as well as among common mass all over the world. Although there are few other sports that has gained popularity in different subcontinents here and there in last few decades but none of them have ever dared to challenge the popularity of football anytime in the past or at present. In fact the popularity and attraction for both football and footballers has increased exponentially over the past few decades with the introduction of humongous platforms like "World Cup Football" organized by prestigious association like FIFA and support from various other independent affluent football clubs. Today, it has become the sign of dignity and status symbol for a country to host a mega-event like World Cup Football and take advantage of the tourism and business opportunities associated with it. Behind the scene a country can showcase the strength of it's infrastructure and attract foreign tourists & investors and can create huge business opportunities by hosting such an event.

Siri, Alexa and Cortana all started out as female. Now a group of marketing executives, tech experts and academics are trying to make virtual assistants more egalitarian. Siri, Alexa and Cortana all started out as female. Now a group of marketing executives, tech experts and academics are trying to make virtual assistants more egalitarian. Have you ever noticed something most virtual assistants have in common?