Next-generation wireless networks must support ultra-reliable, low-latency communication and intelligently manage a massive number of Internet of Things (IoT) devices in real-time, within a highly dynamic environment. This need for stringent communication quality-of-service (QoS) requirements as well as mobile edge and core intelligence can only be realized by integrating fundamental notions of artificial intelligence (AI) and machine learning across the wireless infrastructure and end-user devices. In this context, this paper provides a comprehensive tutorial that introduces the main concepts of machine learning, in general, and artificial neural networks (ANNs), in particular, and their potential applications in wireless communications. For this purpose, we present a comprehensive overview on a number of key types of neural networks that include feed-forward, recurrent, spiking, and deep neural networks. For each type of neural network, we present the basic architecture and training procedure, as well as the associated challenges and opportunities. Then, we provide an in-depth overview on the variety of wireless communication problems that can be addressed using ANNs, ranging from communication using unmanned aerial vehicles to virtual reality and edge caching.For each individual application, we present the main motivation for using ANNs along with the associated challenges while also providing a detailed example for a use case scenario and outlining future works that can be addressed using ANNs. In a nutshell, this article constitutes one of the first holistic tutorials on the development of machine learning techniques tailored to the needs of future wireless networks.

Time series forecasting is an important problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. In this paper, we propose to tackle such forecasting problem with Transformer. Although impressed by its performance in our preliminary study, we found its two major weaknesses: (1) locality-agnostics: the point-wise dot-product self attention in canonical Transformer architecture is insensitive to local context, which can make the model prone to anomalies in time series; (2) memory bottleneck: space complexity of canonical Transformer grows quadratically with sequence length $L$, making modeling long time series infeasible. In order to solve these two issues, we first propose convolutional self attention by producing queries and keys with causal convolution so that local context can be better incorporated into attention mechanism. Then, we propose LogSparse Transformer with only $O(L(\log L)^{2})$ memory cost, improving the time series forecasting in finer granularity under constrained memory budget. Our experiments on both synthetic data and real-world datasets show that it compares favorably to the state-of-the-art.

Census data provide detailed information about population characteristics at a coarse resolution. Nevertheless, fine-grained, high-resolution mappings of population counts are increasingly needed to characterize population dynamics and to assess the consequences of climate shocks, natural disasters, investments in infrastructure, development policies, etc. Dissagregating these census is a complex machine learning, and multiple solutions have been proposed in past research. We propose in this paper to view the problem in the context of the aggregate learning paradigm, where the output value for all training points is not known, but where it is only known for aggregates of the points (i.e. in this context, for regions of pixels where a census is available). We demonstrate with a very simple and interpretable model that this method is on par, and even outperforms on some metrics, the state-of-the-art, despite its simplicity.

Leaders from the G20 nations will meet in Osaka, Japan, this week at a time when some of the core values of the organization, such as free trade and an environmentally sustainable future, are being challenged. The forum, originally established to ensure global financial stability, will feature discussions around eight main themes this year, including the global economy, women's empowerment, and energy and the environment. Pew Research Center conducted public opinion surveys in many of the G20 member nations in 2018. Based on these surveys, here is a look at the way people in these countries view some of the central issues that will be addressed at this year's summit. G20 leaders previously committed to a 25% reduction in the gap between the shares of men and women participating in their countries' labor forces by 2025.

The cost of wind energy can be reduced by using SCADA data to detect faults in wind turbine components. Normal behavior models are one of the main fault detection approaches, but there is a lack of consensus in how different input features affect the results. In this work, a new taxonomy based on the causal relations between the input features and the target is presented. Based on this taxonomy, the impact of different input feature configurations on the modelling and fault detection performance is evaluated. To this end, a framework that formulates the detection of faults as a classification problem is also presented.

We tune one of the most common heating, ventilation, and air conditioning (HVAC) control loops, namely the temperature control of a room. For economical and environmental reasons, it is of prime importance to optimize the performance of this system. Buildings account from 20 to 40% of a country energy consumption, and almost 50% of it comes from HVAC systems. Scenario projections predict a 30% decrease in heating consumption by 2050 due to efficiency increase. Advanced control techniques can improve performance; however, the proportional-integral-derivative (PID) control is typically used due to its simplicity and overall performance. We use Safe Contextual Bayesian Optimization to optimize the PID parameters without human intervention. We reduce costs by 32% compared to the current PID controller setting while assuring safety and comfort to people in the room. The results of this work have an immediate impact on the room control loop performances and its related commissioning costs. Furthermore, this successful attempt paves the way for further use at different levels of HVAC systems, with promising energy, operational, and commissioning costs savings, and it is a practical demonstration of the positive effects that Artificial Intelligence can have on environmental sustainability.

In an acerbic 1976 article on AI research, the computer scientist Drew McDermott was the first to contrast the phrases "artificial intelligence" and "natural stupidity". Four decades later, researchers warn of the threat posed by computer "superintelligence", but stupidity is still a far greater peril: both the age-old natural stupidity of humans and the newfangled artificial stupidity displayed by algorithms – such as chatbots supposed to be able to diagnose illness, or facial-recognition software that throws up false matches for ethnic minorities – in which we place far too much trust. An alternative reason to be cheerful about the coming machine takeover is offered here by the eminent scientist and inventor James Lovelock. A chemist by training, who invented instruments for Mars rovers and helped to discover the depletion of the ozone layer, Lovelock is most celebrated in pop culture for his "Gaia hypothesis". First formulated in the 1960s, it proposes that Earth and its biosphere comprise a single, self-regulating system.

To achieve untethered flight, this latest iteration of the Robobee underwent several important changes, including the addition of a second pair of wings. The change from two to four wings, along with less visible changes to the actuator and transmission ratio, made the vehicle more efficient, gave it more lift, and allowed us to put everything we need on-board without using more power, the team said. The extra lift, with no additional power requirements, allowed the researchers to cut the power cord -- which has kept the Robobee tethered for nearly a decade -- and attach solar cells and an electronics panel to the vehicle. The solar cells, the smallest commercially available, weigh 10 milligrams each and get 0.76 milliwatts per milligram of power when the sun is at full intensity. The Robobee X-Wing needs the power of about three Earth suns to fly, making outdoor flight out of reach for now.

Wait, the AI advantage is already here and gone? That's what Deloitte warns in their report "Future in the balance? How countries are pursuing an AI advantage".A noteworthy quote: "There are indications that the window for competitive differentiation with AI is rapidly closing. As AI technologies become easier to consume and get embedded in an increasing number of products and services, the early-mover advantage will rapidly diminish" (see Figure 1). How Countries are Pursuing an AI Advantage". But of course, it's not too late to benefit from the digital transformation potential of AI! Because having AI capabilities is not the same thing as exploiting AI capabilities. "AI success depends on getting the execution right.

A solar-powered flying robot has become the lightest machine capable of flying without an attached power source. Weighing just 259 milligrams, the insect-inspired RoboBee X-Wing has four wings that flap at a rate of 170 times per second. It has a wingspan of 3.5 centimetres and is 6.5 cemtimetres high. The flying robot was developed by Noah Jafferis and colleagues at Harvard University. Its wings are controlled by two muscle-like plates that contract when voltage passes through them.