British archaeologists who discovered hundreds of artefacts from a cluster of 17th century shipwrecks in the Mediterranean Sea have had their cargo seized and been accused of an'illicit excavation'. Enigma Recoveries, which led an expedition into the Levantine Basin off the coast of Cyprus, found 12 shipwrecks filled with Chinese porcelain, jugs, coffee pots, peppercorns and illicit tobacco pipes. The ships and their priceless cargo, hailed as the'archaeological equivalent of finding a new planet' were recovered in ancient'shipping lanes' that served spice and silk trades from 300 BC onwards. But in a strongly-worded statement, the Cypriot government accused the company of being well known to both Cyprus and UNESCO for its'illicit underwater excavations' and its'violent extraction of objects causing destruction to their context'. Cyprus's Department of Antiquities accused the company of intending to sell the objects, as allegedly evident in documents filed with the United States Securities and Exchange Commission (NASDAQ).

Machine reading comprehension (MRC) aims to teach machines to read and comprehend human languages, which is a long-standing goal of natural language processing (NLP). With the burst of deep neural networks and the evolution of contextualized language models (CLMs), the research of MRC has experienced two significant breakthroughs. MRC and CLM, as a phenomenon, have a great impact on the NLP community. In this survey, we provide a comprehensive and comparative review on MRC covering overall research topics about 1) the origin and development of MRC and CLM, with a particular focus on the role of CLMs; 2) the impact of MRC and CLM to the NLP community; 3) the definition, datasets, and evaluation of MRC; 4) general MRC architecture and technical methods in the view of two-stage Encoder-Decoder solving architecture from the insights of the cognitive process of humans; 5) previous highlights, emerging topics, and our empirical analysis, among which we especially focus on what works in different periods of MRC researches. We propose a full-view categorization and new taxonomies on these topics. The primary views we have arrived at are that 1) MRC boosts the progress from language processing to understanding; 2) the rapid improvement of MRC systems greatly benefits from the development of CLMs; 3) the theme of MRC is gradually moving from shallow text matching to cognitive reasoning.

The last German military communications decoded at Bletchley Park in World War Two have been revealed to mark the 75th anniversary of VE Day. They were broadcast on 7 May 1945 by a military radio network making its final stand in Cuxhaven on Germany's North Sea coast. The message reports the arrival of British troops and ends: "Closing down for ever - all the best - goodbye." After Germany surrendered, VE Day was declared the next day. In 1944, this German military radio network, codenamed BROWN, had extended across Europe sending reports about the development of experimental weapons.

The Internet-of-Things generates vast quantities of data, much of it attributable to an individual's activity and behaviour. Holding and processing such personal data in a central location presents a significant privacy risk to individuals (of being identified or of their sensitive data being leaked). However, analytics based on machine learning and in particular deep learning benefit greatly from large amounts of data to develop high performance predictive models. Traditionally, data and models are stored and processed in a data centre environment where models are trained in a single location. This work reviews research around an alternative approach to machine learning known as federated learning which seeks to train machine learning models in a distributed fashion on devices in the user's domain, rather than by a centralised entity. Furthermore, we review additional privacy preserving methods applied to federated learning used to protect individuals from being identified during training and once a model is trained. Throughout this review, we identify the strengths and weaknesses of different methods applied to federated learning and finally, we outline future directions for privacy preserving federated learning research, particularly focusing on Internet-of-Things applications.

Archaeologists have found shipwrecks in the Mediterranean filled with hundreds of artefacts including Chinese porcelain, jugs, coffee pots, peppercorns and illicit tobacco pipes. A British-led expedition found a cluster of 12 ships on the sea bed, 1.2 miles below the surface of the Levantine Sea, using sophisticated robots. The ships were recovered in ancient'shipping lanes' that served spice and silk trades of the Greek, Roman and Ottoman empires, from 300 BC onwards. The ancient ships – including the biggest ever found in the Med – were unearthed in a muddy part of the eastern seabed between Cyprus and Lebanon, where remnants are often hard to find. The cluster of shipwrecks were found in the Levantine Basin in the east of the Mediterranean Sea.

Researchers say evaluating the'social-connectedness' of regions using Facebook data could give epidemiologists another tool in judging the spread of infectious disease outside of geographic proximity and population density. The study, which appears in the preprint journal ArXiv and is authored by researchers from New York University, found links between two hotspots of the ongoing COVID-19 pandemic - Westchester County, New York and Lodi province in Italy - to areas with correlating connections on the social media platform, Facebook. Using an equation developed by the same researchers in 2017 called the'Social Connectedness Index' the study was able to make correlations between the spread of COVID-19 from Westchester County and Lodi to geographically disparate locations like ski resorts on Florida and vacation spots in Rimini, Italy near the Adriatic sea. Those correlations remained even after controlling for wealth, population density, and geographic proximity according to researchers. Levels of social connectedness didn't always correlate to the disproportionate spread of the virus, however.

In most real-world applications, it is seldom the case that a given observable evolves independently of its environment. In social networks, users' behavior results from the people they interact with, news in their feed, or trending topics. In natural language, the meaning of phrases emerges from the combination of words. In general medicine, a diagnosis is established on the basis of the interaction of symptoms. Here, we propose a new model, the Interactive Mixed Membership Stochastic Block Model (IMMSBM), which investigates the role of interactions between entities (hashtags, words, memes, etc.) and quantifies their importance within the aforementioned corpora. We find that interactions play an important role in those corpora. In inference tasks, taking them into account leads to average relative changes with respect to non-interactive models of up to 150\% in the probability of an outcome. Furthermore, their role greatly improves the predictive power of the model. Our findings suggest that neglecting interactions when modeling real-world phenomena might lead to incorrect conclusions being drawn.

With the rapid emergence of deep learning (DL) technology, it has been successfully used in various fields including aquaculture. This change can create new opportunities and a series of challenges for information and data processing in smart fish farming. This paper focuses on the applications of DL in aquaculture, including live fish identification, species classification, behavioral analysis, feeding decision-making, size or biomass estimation, water quality prediction. In addition, the technical details of DL methods applied to smart fish farming are also analyzed, including data, algorithms, computing power, and performance. The results of this review show that the most significant contribution of DL is the ability to automatically extract features. However, challenges still exist; DL is still in an era of weak artificial intelligence. A large number of labeled data are needed for training, which has become a bottleneck restricting further DL applications in aquaculture. Nevertheless, DL still offers breakthroughs in the handling of complex data in aquaculture. In brief, our purpose is to provide researchers and practitioners with a better understanding of the current state of the art of DL in aquaculture, which can provide strong support for the implementation of smart fish farming.

Access to a fast and easily copied forward model of a game is essential for model-based reinforcement learning and for algorithms such as Monte Carlo tree search, and is also beneficial as a source of unlimited experience data for model-free algorithms. Learning forward models is an interesting and important challenge in order to address problems where a model is not available. Building upon previous work on the Neural GPU, this paper introduces the Neural Game Engine, as a way to learn models directly from pixels. The learned models are able to generalise to different size game levels to the ones they were trained on without loss of accuracy. Results on 10 deterministic General Video Game AI games demonstrate competitive performance, with many of the games models being learned perfectly both in terms of pixel predictions and reward predictions. The pre-trained models are available through the OpenAI Gym interface and are available publicly for future research here: \url{https://github.com/Bam4d/Neural-Game-Engine}

We propose a generative model for the spatio-temporal distribution of high dimensional categorical observations. These are commonly produced by robots equipped with an imaging sensor such as a camera, paired with an image classifier, potentially producing observations over thousands of categories. The proposed approach combines the use of Dirichlet distributions to model sparse co-occurrence relations between the observed categories using a latent variable, and Gaussian processes to model the latent variable's spatio-temporal distribution. Experiments in this paper show that the resulting model is able to efficiently and accurately approximate the temporal distribution of high dimensional categorical measurements such as taxonomic observations of microscopic organisms in the ocean, even in unobserved (held out) locations, far from other samples. This work's primary motivation is to enable deployment of informative path planning techniques over high dimensional categorical fields, which until now have been limited to scalar or low dimensional vector observations.