With two months to go until Samsung unveils its next flagship phone – presumably called the Galaxy S10 – we already know almost everything there is to know. A slew of leaks and rumours mean little has been left to the imagination about the iPhone rival, with the latest leak revealing the lengths the South Korean electronic giant has gone to avoid the "notch" design. For several years, smartphone manufacturers have been getting closer and closer to making an all-screen device, though necessary front-facing technologies like cameras and sensors have proved a major obstacle to achieving this goal. Apple's answer was to include a notch at the top of the screen, which it unveiled pm the iPhone X in 2017 to widespread acclaim. Not everyone was impressed and Samsung took the opportunity to mock its chief rival.

When T-Mobile's chief executive went before Senate lawmakers this year to make the case for his company's merger with Sprint, he argued that the deal could help preserve U.S. dominance in high-tech wireless networks for smartphones and other devices. "We'll make sure America wins the global 5G race," John Legere vowed. "5G will unlock capabilities that will fuel job creation and innovation well beyond what we have seen so far." The entire industry has spent much of the year marketing a dazzling future to consumers, one in which the successor to 4G LTE enables entirely new technologies, such as self-driving cars and remote medicine. But despite the hype, 5G is still a long way from becoming a reality for the majority of everyday Americans.

Small base stations (SBs) of fifth-generation (5G) cellular networks are envisioned to have storage devices to locally serve requests for reusable and popular contents by \emph{caching} them at the edge of the network, close to the end users. The ultimate goal is to shift part of the predictable load on the back-haul links, from on-peak to off-peak periods, contributing to a better overall network performance and service experience. To enable the SBs with efficient \textit{fetch-cache} decision-making schemes operating in dynamic settings, this paper introduces simple but flexible generic time-varying fetching and caching costs, which are then used to formulate a constrained minimization of the aggregate cost across files and time. Since caching decisions per time slot influence the content availability in future slots, the novel formulation for optimal fetch-cache decisions falls into the class of dynamic programming. Under this generic formulation, first by considering stationary distributions for the costs and file popularities, an efficient reinforcement learning-based solver known as value iteration algorithm can be used to solve the emerging optimization problem. Later, it is shown that practical limitations on cache capacity can be handled using a particular instance of the generic dynamic pricing formulation. Under this setting, to provide a light-weight online solver for the corresponding optimization, the well-known reinforcement learning algorithm, $Q$-learning, is employed to find optimal fetch-cache decisions. Numerical tests corroborating the merits of the proposed approach wrap up the paper.

Japanese startup Groove X, founded by an alumni of SoftBank Group Corp's robotics unit, unveiled its first creation on Tuesday - a companion robot designed to make users happy. The Lovot, an amalgam of'love' and'robot', cannot help with the housework but it will'draw out your ability to love,' Groove X founder and CEO Kaname Hayashi told reporters at the launch in Tokyo. Using artificial intelligence (AI) to interact with its surroundings, the wheeled machine resembles a penguin with cartoonish human eyes, has interchangeable outfits and communicates in squeaks. Groove X's Lovot robots are displayed at their demonstration during the launch event in Tokyo. Using artificial intelligence (AI) to interact with its surroundings, the wheeled machine resembles a penguin with cartoonish human eyes, has interchangeable outfits and communicates in squeaks.

Motivated by the prediction of cell loads in cellular networks, we formulate the following new, fundamental problem of statistical learning of geometric marks of point processes: An unknown marking function, depending on the geometry of point patterns, produces characteristics (marks) of the points. One aims at learning this function from the examples of marked point patterns in order to predict the marks of new point patterns. To approximate (interpolate) the marking function, in our baseline approach, we build a statistical regression model of the marks with respect some local point distance representation. In a more advanced approach, we use a global data representation via the scattering moments of random measures, which build informative and stable to deformations data representation, already proven useful in image analysis and related application domains. In this case, the regression of the scattering moments of the marked point patterns with respect to the non-marked ones is combined with the numerical solution of the inverse problem, where the marks are recovered from the estimated scattering moments. Considering some simple, generic marks, often appearing in the modeling of wireless networks, such as the shot-noise values, nearest neighbour distance, and some characteristics of the Voronoi cells, we show that the scattering moments can capture similar geometry information as the baseline approach, and can reach even better performance, especially for non-local marking functions. Our results motivate further development of statistical learning tools for stochastic geometry and analysis of wireless networks, in particular to predict cell loads in cellular networks from the locations of base stations and traffic demand.

SK Telecom announced on Saturday that it has switched on its commercial 5G network, marking the occasion with a call from CEO Park Jung-ho in Bundang to Myeondong, using a Samsung 5G smartphone prototype. SK Telecom's 5G network currently covers main areas of 13 cities and counties nationwide. Mischievously, we would like to think the call went something like "Hello, can anyone hear me? There's no-one there…" That's the problem with launching a brand new network technology – penetration levels are somewhat low. Actually, that first call over its commercial 5G network was made between CEO Park located in Bundang, Gyeonggi-do and SK Telecom Manager Park Sook-hee located in Myeongdong, Seoul.

Smart mobility management would be an important prerequisite for future fog computing systems. In this research, we propose a learning-based handover optimization for the Internet of Vehicles that would assist the smooth transition of device connections and offloaded tasks between fog nodes. To accomplish this, we make use of machine learning algorithms to learn from vehicle interactions with fog nodes. Our approach uses a three-layer feed-forward neural network to predict the correct fog node at a given location and time with 99.2 % accuracy on a test set. We also implement a dual stacked recurrent neural network (RNN) with long short-term memory (LSTM) cells capable of learning the latency, or cost, associated with these service requests. We create a simulation in JAMScript using a dataset of real-world vehicle movements to create a dataset to train these networks. We further propose the use of this predictive system in a smarter request routing mechanism to minimize the service interruption during handovers between fog nodes and to anticipate areas of low coverage through a series of experiments and test the models' performance on a test set.

Millimeter wave (mmWave) communication with large antenna arrays is a promising technique to enable extremely high data rates due to large available bandwidth. Given the knowledge of an optimal directional beamforming vector, large antenna arrays have been shown to overcome both the severe signal attenuation in mmWave. However, fundamental limits and achievable learning of an optimal beamforming vector remain. This paper considers the problem of adaptive and sequential optimization of the beamforming vectors during the initial access phase of communication. With a single-path channel model, the problem is reduced to actively learning the Angle-of-Arrival (AoA) of the signal sent from the user to the Base Station (BS). Drawing on the recent results in the design of a hierarchical beamforming codebook [1], sequential measurement dependent noisy search [2], and active learning from an imperfect labeler [3], an adaptive and sequential alignment algorithm is proposed. For any given resolution and error probability of the estimated AoA, an upper bound on the expected search time of the proposed algorithm is derived via the Extrinsic Jensen Shannon Divergence. The upper bound demonstrates that the search time of the proposed algorithm asymptotically matches the performance of the noiseless bisection search up to a constant factor characterizing the AoA acquisition rate. Furthermore, the acquired AoA error probability decays exponentially fast with the search time with an exponent that is a decreasing function of the acquisition rate.Numerically, the proposed algorithm is compared with prior work where a significant improvement of the system communication rate is observed. Most notably, in the relevant regime of low (- 10dB to 5dB) raw SNR, this establishes the first practically viable solution for initial access and, hence, the first demonstration of stand-alone mmWave communication.

This work develops a deep learning power control framework for energy efficiency maximization in wireless interference networks. Rather than relying on suboptimal power allocation policies, the training of the deep neural network is based on the globally optimal power allocation rule, leveraging a newly proposed branch-and-bound procedure with a complexity affordable for the offline generation of large training sets. In addition, no initial power vector is required as input of the proposed neural network architecture, which further reduces the overall complexity. As a benchmark, we also develop a first-order optimal power allocation algorithm. Numerical results show that the neural network solution is virtually optimal, outperforming the more complex first-order optimal method, while requiring an extremely small online complexity.

Abstract--This work investigates the use of deep learning to perform user-cell association for sum-rate maximization in Massive MIMO networks. It is shown how a deep neural network can be trained to approach the optimal association rule with a much more limited computational complexity, thus enabling to update the association rule in real-time, on the basis of the mobility patterns of users. In particular, the proposed neural network design requires as input only the users' geographical positions. Numerical results show that it guarantees the same performance of traditional optimization-oriented methods. I. INTRODUCTION 5G wireless networks are scheduled to be rolled-out in only a couple of years.