Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e. 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that undergone gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

Inferring air quality from a limited number of observations is an essential task for monitoring and controlling air pollution. Existing inference methods typically use low spatial resolution data collected by fixed monitoring stations and infer the concentration of air pollutants using additional types of data, e.g., meteorological and traffic information. In this work, we focus on street-level air quality inference by utilizing data collected by mobile stations. We formulate air quality inference in this setting as a graph-based matrix completion problem and propose a novel variational model based on graph convolutional autoencoders. Our model captures effectively the spatio-temporal correlation of the measurements and does not depend on the availability of additional information apart from the street-network topology. Experiments on a real air quality dataset, collected with mobile stations, shows that the proposed model outperforms state-of-the-art approaches.

In multi-agent reinforcement learning, centralised policies can only be executed if agents have access to either the global state or an instantaneous communication channel. An alternative approach that circumvents this limitation is to use centralised training of a set of decentralised policies. However, such policies severely limit the agents' ability to coordinate. We propose multi-agent common knowledge reinforcement learning (MACKRL), which strikes a middle ground between these two extremes. Our approach is based on the insight that, even in partially observable settings, subsets of agents often have some common knowledge that they can exploit to coordinate their behaviour. Common knowledge can arise, e.g., if all agents can reliably observe things in their own field of view and know the field of view of other agents. Using this additional information, it is possible to find a centralised policy that conditions only on agents' common knowledge and that can be executed in a decentralised fashion. A resulting challenge is then to determine at what level agents should coordinate. While the common knowledge shared among all agents may not contain much valuable information, there may be subgroups of agents that share common knowledge useful for coordination. MACKRL addresses this challenge using a hierarchical approach: at each level, a controller can either select a joint action for the agents in a given subgroup, or propose a partition of the agents into smaller subgroups whose actions are then selected by controllers at the next level. While action selection involves sampling hierarchically, learning updates are based on the probability of the joint action, calculated by marginalising across the possible decisions of the hierarchy. We show promising results on both a proof-of-concept matrix game and a multi-agent version of StarCraft II Micromanagement.

The government is launching an inquiry into the use of personal data to set individual prices for holidays, cars and household goods, amid rising fears of a consumer rip-off. The research, supported by the competition watchdog, will explore the prevalence of "dynamic pricing" based on information gathered about an individual, such as location, marital status, birthday or travel history. With about 17% of retail sales now made online, according to the Office for National Statistics, there is rising concern about the use of technology, including artificial intelligence and bots, to "personalise" prices, to the disadvantage of some shoppers. It has become common for online prices to fluctuate depending on time of day or availability – whether for gig tickets or Uber taxis. Now digital labels have begun to appear in shops, offering the potential to bring "surge pricing" into analogue sales.

Every year, the workplace that futurists have long envisioned--one dominated by artificially intelligent machines doing everything from answering the phones to balancing a company's books--inches ever closer to reality. Naturally, we humans are feeling more and more pinched by the rise of AI--a new workforce that doesn't need to sleep, eat, take breaks, socialize, or even receive a paycheck. For many, such a future is a source of genuine anxiety and those starting out in their careers might be forgiven for wondering which jobs are safe from automation. According to the World Economic Forum's The Future Of Jobs Report, within the next five years alone, a majority of companies expect to scale back their full-time workforce to make room for automation. The chief economist for the Bank of England predicted that there might be as many as 80 million jobs automated in the US alone.

The Big Innovation Centre and Deep Knowledge Analytics, in conjunction with the All Party Parliamentary Group on Artificial Intelligence, has released a new report examining the state of the artificial intelligence industry in the United Kingdom. The report is titled "Artificial Intelligence Industry in the UK 2018." The report was released on October 24, 2018. The report was written by Big Innovation Centre CEO Professor Birgitte Andersen and Deep Knowledge Analytics Co-founder Dmitry Kaminskiy. The report examines and profiles around one thousand companies, six hundred investors, and eighty identified influencers.

Editor's Note: We know artificial intelligence will change the very nature of war--but we don't know how. The United States, China, and other powers recognize this transformative potential and, even as they seek to exploit it, fear that others will gain the upper hand in an artificial intelligence arms race. My Brookings colleague Chris Meserole describes how artificial intelligence might produce a new security dilemma and proposes several ways to mitigate the risk. Recent breakthroughs in machine learning and artificial intelligence (A.I.) have prompted breathless speculation about their national security applications. Yet most of that work has focused narrowly on their implications for autonomous weapons systems, rather than on the broader security environment.

Scientists have developed an artificial intelligence system that can help better understand what triggers religious violence. The study, published in The Journal for Artificial Societies and Social Stimulation, focuses on two cases of extreme violence, firstly, the conflict commonly referred to as the Northern Ireland Troubles, which is regarded as one of the most violent periods in Irish history. The conflict, involving the British army and various Republican and Loyalist paramilitary groups, spanned three decades, claimed the lives of approximately 3,500 people and saw a further 47,000 injured. Although a much shorter period of tension, the 2002 Gujarat riots of India were equally devastating. The three-day period of inter-communal violence between the Hindu and Muslim communities in the western Indian state of Gujarat, began when a Sabarmarti Express train filled with Hindu pilgrims, stopped in the, predominantly Muslim town of Godhra, and ended with the deaths of more than 2,000 people.

Artificial intelligence (AI) and machine learning will have a significant impact on the way companies manage their workforces within two years. Research by analyst group Fosway and Unleash reveals that organisations are looking to deploy chatbots and machine learning technology to provide better HR (human resources) services to their employees. The findings come at a time when most HR professionals say their existing systems are not yet ready to meet the needs of the workforce. Technology companies are developing AI, chatbots and natural language processing to make it easier for employers and managers to deal with administrative HR tasks. "For businesses, it will have a significant impact on productivity – people will spend less time trying to do stuff," said David Wilson, founder and CEO of Fosway Group.

Just hearing the words "open enrollment" is enough to make anyone groan with boredom. But what if you could enroll in health insurance at work by talking to a computer? You're asked a few simple questions about your family, your lifestyle and your medical history, and within nine minutes, you're done. Enter Jellyvision and Alex, a virtual benefits counselor powered by artificial intelligence to help employees better understand their benefits packages. In the complicated and ever-evolving landscape of health care, Alex shows employees which medical plans can save them the most money based on their personal situation.