While all my American and UK colleagues have had access to Amazon's Alexa for years, I've been left out of the party here in France. Those devices are now up for pre-order on Amazon at half price, with delivery set at June 13th for Prime members. It took Amazon long enough to teach Alexa French, but the assistant has reportedly gained mastery of both the language and country. "In France, Alexa is French," said Amazon VP Jorrit Van der Meulen. "We've built an entirely new experience from the ground up that honors the French language and culture, allowing customers to just ask to get music, weather, news, information, and more."

Video A drone surveillance system capable of highlighting "violent individuals" in a crowd in real time has been built by eggheads. The artificially intelligent technology uses a video camera on a hovering quadcopter to study the body movements of everyone in view. It then raises an alert when it identifies aggressive actions, such as punching, stabbing, shooting, kicking, and strangling, with an accuracy of about 85 per cent. It doesn't perform any facial recognition – it merely detects possible violence between folks. And its designers believe the system could be expanded to automatically spot people crossing borders illegally, detect kidnappings in public areas, and set off alarms when vandalism is observed.

But such accessories can also be used to hack into phones, and kicking them out as iOS 12 now does will stop them from doing so.

Researchers from the University of Bologna and the Swiss Federal Institute of Technology in Zurich (otherwise known as the ETH Zurich) claim to have engineered the world's smallest autonomous drone, according to a recent report. When it comes to the nano-drone industry, the primary focus of which is to build capable autonomous UAVs with the smallest, most lightweight batteries, this is a milestone. With a smaller battery comes a decrease in power and flight time. For nano-drones, which are defined by maximum four-inch diameters, developing a model somewhere in between these two poles has been a longtime struggle for engineers. The two teams of European researchers may have finally achieved that task, however, by reducing the power requirements of the drone by using a newly-developed processor that can efficiently run the autonomous, artificial intelligence-infused navigation required, according to Fast Company.

It seems some animals may have better manners than some humans. Two-way conversations - once thought to be a trait unique to our species - are common across the animal kingdom. From the whistles of dolphins to the low rumbling of elephants, creatures take turns to'talk' to each other, according to a new study. Animals communicate in a variety of ways, with verbal'talking' among them. Researchers from the Universities of York and Sheffield, the Max Planck Institute for Evolutionary Anthropology in Germany, and the Max Planck Institute for Psycholinguistics in the Netherlands, set out to understand how common this phenomenon was in the animal kingdom.

This paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters. A convolutional neural network is trained on a collection of discrete, parameterizable fluid simulation velocity fields. Due to the capability of deep learning architectures to learn representative features of the data, our generative model is able to accurately approximate the training data set, while providing plausible interpolated in-betweens. The proposed generative model is optimized for fluids by a novel loss function that guarantees divergence-free velocity fields at all times. In addition, we demonstrate that we can handle complex parameterizations in reduced spaces, and advance simulations in time by integrating in the latent space with a second network. Our method models a wide variety of fluid behaviors, thus enabling applications such as fast construction of simulations, interpolation of fluids with different parameters, time re-sampling, latent space simulations, and compression of fluid simulation data. Reconstructed velocity fields are generated up to 700x faster than traditional CPU solvers, while achieving compression rates of over 1300x.

Networks, which represent agents and interactions between them, arise in myriad applications throughout the sciences, engineering, and even the humanities. To understand large-scale structure in a network, a common task is to cluster a network's nodes into sets called "communities" such that there are dense connections within communities but sparse connections between them. A popular and statistically principled method to perform such clustering is to use a family of generative models known as stochastic block models (SBMs). In this paper, we show that maximum likelihood estimation in an SBM is a network analog of a well-known continuum surface-tension problem that arises from an application in metallurgy. To illustrate the utility of this bridge, we implement network analogs of three surface-tension algorithms, with which we successfully recover planted community structure in synthetic networks and which yield fascinating insights on empirical networks from the field of hyperspectral video segmentation.

Differential Privacy is one of the strongest privacy guarantees, which allows the release of useful information about any sensitive dataset. However, it provides the same level of protection for all elements in the data universe. In this paper, we consider $d_{\mathcal{X}}$-privacy, an instantiation of the privacy notion introduced in \cite{chatzikokolakis2013broadening}, which allows specifying a separate privacy budget for each pair of elements in the data universe. We describe a systematic procedure to tailor any existing differentially private mechanism into a $d_{\mathcal{X}}$-private variant for the case of linear queries. For the resulting $d_{\mathcal{X}}$-private mechanisms, we provide theoretical guarantees on the trade-off between utility and privacy, and show that they always outperform their \emph{vanilla} counterpart. We demonstrate the effectiveness of our procedure, by evaluating the proposed $d_{\mathcal{X}}$-private Laplace mechanism on both synthetic and real datasets using a set of randomly generated linear queries.

In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications. However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws intrinsic to the network structures. To address this problem and improve the robustness of neural networks, we investigate the fundamental mechanisms behind adversarial examples and propose a novel robust training method via regulating adversarial gradients. The regulation effectively squeezes the adversarial gradients of neural networks and significantly increases the difficulty of adversarial example generation. Without any adversarial example involved, the robust training method could generate naturally robust networks, which are near-immune to various types of adversarial examples. Experiments show the naturally robust networks can achieve optimal accuracy against Fast Gradient Sign Method (FGSM) and C&W attacks on MNIST, Cifar10, and Google Speech Command dataset. Moreover, our proposed method also provides neural networks with consistent robustness against transferable attacks.

While significant advances have been made in planning and reinforcement learning for robots, these algorithms require access to a reward (or cost) function in order to be successful. Unfortunately, designing a good reward function by hand remains challenging in many tasks. When designing the reward, the goal is to choose a function that guides the robot to accomplish the task in any potential test environment that it might encounter. Typically, the designer considers a representative set of training environments, and finds a reward function that induces desirable behavior across all of them, as in Figure 1 (Top). In practice, this can be both challenging and frustrating for the reward designer. The process often results in many iterations of tuning, whereby changing the reward function corrects the behavior in one environment, but breaks it in another, and so on. We posit that designing a good reward function for a single environment at a time is easier than designing one for all training environments in consideration simultaneously. Imagine the task of motion planning in the home. The reward function provided to the planner must correctly encode the desired tradeoffs: the robot must stay away from static objects, it should give wider berth to fragile objects (as in Figure 1 (Bottom)), and it needs to keep a comfortable distance from the person, prioritizing more sensitive areas, such as the head [9].