To learn useful dynamics on long time scales, neurons must use plasticity rules that account for long-term, circuit-wide effects of synaptic changes. In other words, neural circuits must solve a credit assignment problem to appropriately assign responsibility for global network behavior to individual circuit components. Furthermore, biological constraints demand that plasticity rules are spatially and temporally local; that is, synaptic changes can depend only on variables accessible to the pre- and postsynaptic neurons. While artificial intelligence offers a computational solution for credit assignment, namely backpropagation through time (BPTT), this solution is wildly biologically implausible. It requires both nonlocal computations and unlimited memory capacity, as any synaptic change is a complicated function of the entire history of network activity. Similar nonlocality issues plague other approaches such as FORCE (Sussillo et al. 2009). Overall, we are still missing a model for learning in recurrent circuits that both works computationally and uses only local updates. Leveraging recent advances in machine learning on approximating gradients for BPTT, we derive biologically plausible plasticity rules that enable recurrent networks to accurately learn long-term dependencies in sequential data. The solution takes the form of neurons with segregated voltage compartments, with several synaptic sub-populations that have different functional properties. The network operates in distinct phases during which each synaptic sub-population is updated by its own local plasticity rule. Our results provide new insights into the potential roles of segregated dendritic compartments, branch-specific inhibition, and global circuit phases in learning.

The U.S. and China are locked in an increasingly heated struggle for superpower status. Many perceived this confrontation initially only through the lenses of a trade war. However, the ZTE "saga" already indicated the issue was broader and involved a battle for supremacy over 21st century technologies and, relatedly, for international power (see When AI Started Creating AI – Artificial Intelligence and Computing Power, 7 May 2018). The technological battle increasingly looks like a fight to the death, with the offensive against Huawei, aiming notably to protect future 5G networks (Cassell Bryan-Low, Colin Packham, David Lague, Steve Stecklow And Jack Stubbs, "The China Challenge: the 5G Fight", Reuters Investigates, 21 May 2019). For Huawei and China, as well as for the world, consequences are far reaching, as, after Google "stopping Huawei's Android license", and an Intel and Qualcomm ban, the British chip designer ARM, held notably by Japanese Softbank, now stops relations with Huawei (Paul Sandle, "ARM supply halt deals fresh blow to Chinese tech giant Huawei", Reuters, 22 May 2019; "DealBook Briefing: The Huawei Backlash Goes Global", The New York Times, 23 May 2019; Tom Warren, "Huawei's Android And Windows Alternatives Are Destined For Failure", The Verge, 23 May 2019). The highly possible coming American move against Chinese Hikvision, one of the largest world producers of video surveillance systems involving notably "artificial intelligence, speech monitoring and genetic testing" would only further confirm the American offensive (Doina Chiacu, Stella Qi, "Trump says'dangerous' Huawei could be included in U.S.-China trade deal", Reuters, 23 May 2019; Ana Swanson and Edward Wong, "Trump Administration Could Blacklist China's Hikvision, a Surveillance Firm", The New York Times, 21 May 2019). China, for its part, answers to both the trade war and the technological fight with an ideologically martial mobilisation of its population along the lines of "People's War", "The Long March", and changing TV scheduling to broadcast war films (Iris Zhao and Alan Weedon, "Chinese television suddenly switches scheduling to anti-American films amid US-China trade war", ABC News, 20 May 2019; Michael Martina, David Lawder, "Prepare for difficult times, China's Xi urges as trade war simmers", Reuters, 22 May 2019). This highlights how much is as stake for the Middle Kingdom, as we explained previously ( Sensor and Actuator (4): Artificial Intelligence, the Long March towards Advanced Robots and Geopolitics).

GSMA Director General Mats Granryd outlines 5G's brisk growth since the beginning of 2018, and shares his excitement about how the combination of intelligent connectivity will create smarter applications that make life better and safer. I ntelligent connectivity enables transformational capabilities in transport, entertainment, industry, and much more. For technical systems to digitally match human actions with connected environments, however, they must meet the speed of our natural reaction times. They will also rely on cost-effective edge infrastructure to enable scaling. According to GSMA, 5G could account for as many as 1.4 billion connections by 2025.

Learning the optimized solution as a function of environmental parameters is effective in solving numerical optimization in real time for time-sensitive applications. Existing works of learning to optimize train deep neural networks (DNN) with labels, and the learnt solution are inaccurate, which cannot be employed to ensure the stringent quality of service. In this paper, we propose a framework to learn the latent function with unsupervised deep learning, where the property that the optimal solution should satisfy is used as the "supervision signal" implicitly. The framework is applicable to both functional and variable optimization problems with constraints. We take a variable optimization problem in ultra-reliable and low-latency communications as an example, which demonstrates that the ultra-high reliability can be supported by the DNN without supervision labels.

Today at the Microsoft Build developer conference, we are announcing a partnership with Qualcomm, one of the largest mobile and IoT chipset manufacturers in the world, to jointly create a vision AI developer kit. This will empower Qualcomm's latest AI hardware accelerators to deliver real-time AI on devices without the need for constant connectivity to the cloud or expensive machines. This vision AI developer kit brings all the key hardware and software required to develop camera-based IoT solutions using Azure IoT Edge and Azure Machine Learning (ML) – helping innovators deliver the next generation of AI-enabled robotics, industrial safety, retail, home and enterprise security cameras, smart home devices and more. This is a crucial step toward enabling developers to easily create, manage and monitor AI on the edge. This partnership allows developers to start building AI offerings with prebuilt solutions -- including customizable models -- or create new AI models and deploy directly to the cloud or to the new hardware accelerated devices.

Some companies have created apps that use artificial intelligence to help people text and communicate better. NPR's Susan Davis speaks to journalist Rainesford Stauffer about this AI trend.

The traditional directed acyclic graph (DAG) model assumes data are generated independently from the underlying joint distribution defined by the DAG. In many applications, however, individuals are linked via a network and thus the independence assumption does not hold. We propose a novel Gaussian DAG model for network data, where the dependence among individual data points (row covariance) is modeled by an undirected graph. Under this model, we develop a maximum penalized likelihood method to estimate the DAG structure and the row correlation matrix. The algorithm iterates between a decoupled lasso regression step and a graphical lasso step. We show with extensive simulated and real network data, that our algorithm improves the accuracy of DAG structure learning by leveraging the information from the estimated row correlations. Moreover, we demonstrate that the performance of existing DAG learning methods can be substantially improved via de-correlation of network data with the estimated row correlation matrix from our algorithm.

T-Mobile prides itself on being a disruptor in the world of wireless communications, always thinking creatively about the relationship it wants to have with its consumers. That includes the company's approach to using AI for customer service. Using the predictive capabilities of machine learning to improve customer service is a great example of AI augmenting human abilities. T-Mobile sees it as an opportunity to serve customers better and faster, benefiting not just the company and its service agents but also enriching the customer experience and creating stronger human-to-human connections. "Most industries have looked to use AI and machine learning to build more sophisticated Interactive Voice Response (IVR) systems and chatbots as a means to deflect for as long as possible the interaction between a human customer service agent and the customer," says Cody Sanford, executive vice president and chief information officer at T-Mobile.

Wireless carriers around the world are beginning to deploy 5G, the latest and greatest in mobile broadband technology. Like the evolution from 3G to 4G, the jump to 5G will mean faster speeds, lower latency and many other benefits. It'll be a major boost for businesses, gamers, livestreamers and more. It could be a huge leap in other ways, too -- 5G is so much faster than 4G, and has so much less latency, that it could become the platform for all sorts of new services. Of course, there are also downsides.

With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet-of-Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions Bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new inter-discipline, edge AI or edge intelligence, is beginning to receive a tremendous amount of interest. However, research on edge intelligence is still in its infancy stage, and a dedicated venue for exchanging the recent advances of edge intelligence is highly desired by both the computer system and artificial intelligence communities. To this end, we conduct a comprehensive survey of the recent research efforts on edge intelligence. Specifically, we first review the background and motivation for artificial intelligence running at the network edge. We then provide an overview of the overarching architectures, frameworks and emerging key technologies for deep learning model towards training/inference at the network edge. Finally, we discuss future research opportunities on edge intelligence. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions and inspire further research ideas on edge intelligence.