This document was written by the High-Level Expert Group on AI (AI HLEG). It is the second deliverable of the AI HLEG and follows the publication of the group's first deliverable, Ethics Guidelines for Trustworthy AI, published on 8 April 2019. The AI HLEG is an independent expert group that was set up by the European Commission in June 2018.

A new app can help give you the perfect Instagram shot by removing bystanders and tourists from photos in busy locations. Named Bye Bye Camera, the developer describes it as an art project and an app'for the post-human era'. Artist Damjanski created the software with Do Something Good, an'incubation collective' where coders and artists pool their resources to create projects. The app uses the same AI tools found in facial recognition software to identify people using an object detection algorithm called YOLO (You Only Look Once). It then uses a separate tool to fill in the space left behind with what Adobe has dubbed'context-aware fill'.

The CEO of Instagram has defended the company's decision not to take down a deepfaked video of Mark Zuckerberg two weeks after the doctored video was reported. Adam Mosseri told CBS' Gayle King - in his first US television interview since taking over the platform last year - that the company hasn't yet formulated an official policy on AI-altered video called'deepfakes', and until then taking action would be'inappropriate.' Mosseri said, 'I don't feel good about it,' but said there is no rush to remove the video, in part because'the damage is done.' Mosseri's comments about deepfakes come as a response to King's questioning about a faked video of Facebook CEO Mark Zuckerberg taken from an actual interview with CBSN in 2017. The doctored video features a fairly convincing Zuckerberg next to a superimposed CBSN logo talking about how Facebook wields power over its users.

TEHRAN - Iran said Tuesday it will further free itself from the 2015 nuclear deal in defiance of new American sanctions as U.S. President Donald Trump warned the Islamic republic of "overwhelming" retaliation for any attacks. Tensions between Iran and the U.S. have spiraled since last year when Trump withdrew the United States from the deal under which Tehran was to curb its nuclear program in exchange for relief from economic sanctions. The two arch-rivals have been locked in an escalating war of words since Iran shot down a U.S. surveillance drone in what it said was its own airspace, a claim the US vehemently denies. On Monday, Washington stepped up pressure by blacklisting Iran's supreme leader Ayatollah Ali Khamenei and top military chiefs, saying it would also sanction Foreign Minister Mohammad Javad Zarif later in the week. Tehran was defiant on Tuesday, saying the new US sanctions against Iran showed Washington was "lying" about an offer of talks.

Members of the public are getting the chance to take a free ride in a self-driving car in Detroit as part of a nonprofit coalition's effort to clear up misunderstanding and confusion about the technology (April 5) AP, AP Fully autonomous vehicles that can drive themselves in nearly any situation aren't roaming the streets just yet, but almost every major technology company and automaker is working on getting to that point as quickly as possible. These companies are making huge strides in creating a world where we can hop into a car, tell it where to take us, and safely arrive – with no human input needed. If you need some convincing about how these vehicles will transform our world, consider these four hard-to-believe facts. Research from IHS Markit shows that in nearly two decades, more than 30 million self-driving vehicles will be sold each year. That means that 26% of new cars will have autonomous mobility by that year.

Characterization of a non-Gaussian channelized conductivity field in subsurface flow and transport modeling through inverse modeling usually leads to a high-dimensional inverse problem and requires repeated evaluations of the forward model. In this study, we develop a convolutional adversarial autoencoder (CAAE) network to parameterize the high-dimensional non-Gaussian conductivity fields using a low-dimensional latent representation and a deep residual dense convolutional network (DRDCN) to efficiently construct a surrogate model for the forward model. The two networks are both based on a multilevel residual learning architecture called residual-in-residual dense block. The multilevel residual learning strategy and the dense connection structure in the dense block ease the training of deep networks, enabling us to efficiently build deeper networks that have an essentially increased capacity for approximating mappings of very high-complexity. The CCAE and DRDCN networks are incorporated into an iterative local updating ensemble smoother to formulate an inversion framework. The integrated method is demonstrated using a synthetic solute transport model. Results indicate that CAAE is a robust parameterization method for the channelized conductivity fields with Gaussian conductivities within each facies. The DRDCN network is able to obtain an accurate surrogate model of the forward model with high-dimensional and highly-complex concentration fields using relatively limited training data. The CAAE paramterization approach and the DRDCN surrogate method together significantly reduce the number of forward model runs required to achieve accurate inversion results.

Cluster analysis which focuses on the grouping and categorization of similar elements is widely used in various fields of research. Inspired by the phenomenon of atomic fission, a novel density-based clustering algorithm is proposed in this paper, called fission clustering (FC). It focuses on mining the dense families of a dataset and utilizes the information of the distance matrix to fissure clustering dataset into subsets. When we face the dataset which has a few points surround the dense families of clusters, K-nearest neighbors local density indicator is applied to distinguish and remove the points of sparse areas so as to obtain a dense subset that is constituted by the dense families of clusters. A number of frequently-used datasets were used to test the performance of this clustering approach, and to compare the results with those of algorithms. The proposed algorithm is found to outperform other algorithms in speed and accuracy.

We consider the problem of learning the link parameters as well as the structure of a binary-valued pairwise Markov model. We propose a method based on $l_1$- regularized logistic regression, which estimate globally the whole set of edges and link parameters. Unlike the more recent methods discussed in literature that learn the edges and the corresponding link parameters one node at a time, in this work we propose a method that learns all the edges and corresponding link parameters simultaneously for all nodes, in a global manner. The idea behind this proposal is to exploit the reciprocal information of the nodes between each other during the estimation process. Detailed numerical experiments highlight the advantage of this technique and confirm the intuition behind it.

The rise in popularity of major social media platforms have enabled people to share photos and textual information about their daily life. One of the popular topics about which information is shared is food. Since a lot of media about food are attributed to particular locations and restaurants, information like popularity of spatio-temporal popularity of various cuisines can be analysed. Tracking the popularity of food types and retail locations across space and time can also be useful for business owners and restaurant investors. In this work, we present an approach using off-the shelf machine learning techniques to identify trends and popularity of cuisine types in an area using geo-tagged data from social media, Google images and Yelp. After adjusting for time, we use the Kernel Density Estimation to get hot spots across the location and model the dependencies among food cuisines popularity using Bayesian Networks. We consider the Manhattan borough of New York City as the location for our analyses but the approach can be used for any area with social media data and information about retail businesses.

In our connected world, services are expected to be delivered at speed through multiple means with seamless communication. To put it in day to day conversational terms, 'there is an app for it' attitude prevails. Several technologies are needed to meet this growing demand and indeed these technologies are being developed. The first noteworthy is Internet of Things (IoT), which is in itself coupled technologies to deliver seamless communication with 'anywhere, anytime' as an underlying objective. The 'anywhere, anytime' service delivery paradigm requires a new type of smart systems in developing these services with better capabilities to interact with the human user, such as personalisation, affect state recognition, etc. Here enter cognitive systems, where AI meets cognitive sciences (e.g. cognitive psychology, linguistics, social cognition, etc.). In this paper we will examine the requirements imposed by smart cities development, e.g. intelligent logistics, sensor networks and domestic appliances connectivity, data streams and media delivery, to mention but few. Then we will explore how cognitive systems can meet the challenges these requirements present to the development of new systems. Throughout our discussion here, examples from our recent and current projects will be given supplemented by examples from the literature.