Abductive reasoning generates explanatory hypotheses for new observations using prior knowledge. This paper investigates the use of forgetting, also known as uniform interpolation, to perform ABox abduction in description logic (ALC) ontologies. Non-abducibles are specified by a forgetting signature which can contain concept, but not role, symbols. The resulting hypotheses are semantically minimal and each consist of a set of disjuncts. These disjuncts are each independent explanations, and are not redundant with respect to the background ontology or the other disjuncts, representing a form of hypothesis space. The observations and hypotheses handled by the method can contain both atomic or complex ALC concepts, excluding role assertions, and are not restricted to Horn clauses. Two approaches to redundancy elimination are explored for practical use: full and approximate. Using a prototype implementation, experiments were performed over a corpus of real world ontologies to investigate the practicality of both approaches across several settings.

Anomaly detection in supercomputers is a very difficult problem due to the big scale of the systems and the high number of components. The current state of the art for automated anomaly detection employs Machine Learning methods or statistical regression models in a supervised fashion, meaning that the detection tool is trained to distinguish among a fixed set of behaviour classes (healthy and unhealthy states). We propose a novel approach for anomaly detection in High Performance Computing systems based on a Machine (Deep) Learning technique, namely a type of neural network called autoencoder. The key idea is to train a set of autoencoders to learn the normal (healthy) behaviour of the supercomputer nodes and, after training, use them to identify abnormal conditions. This is different from previous approaches which where based on learning the abnormal condition, for which there are much smaller datasets (since it is very hard to identify them to begin with). We test our approach on a real supercomputer equipped with a fine-grained, scalable monitoring infrastructure that can provide large amount of data to characterize the system behaviour. The results are extremely promising: after the training phase to learn the normal system behaviour, our method is capable of detecting anomalies that have never been seen before with a very good accuracy (values ranging between 88% and 96%).

The seminaïve algorithm can be used to materialise all consequences of a datalog program, and it also forms the basis for algorithms that incrementally update a materialisation as the input facts change. Certain (combinations of) rules, however, can be handled much more efficiently using custom algorithms. To integrate such algorithms into a general reasoning approach that can handle arbitrary rules, we propose a modular framework for computing and maintaining a materialisation. We split a datalog program into modules that can be handled using specialised algorithms, and we handle the remaining rules using the seminaïve algorithm. We also present two algorithms for computing the transitive and the symmetric-transitive closure of a relation that can be used within our framework. Finally, we show empirically that our framework can handle arbitrary datalog programs while outperforming existing approaches, often by orders of magnitude.

We present a novel algorithm to train a deep Q-learning agent using natural-gradient techniques. We compare the original deep Q-network (DQN) algorithm to its natural-gradient counterpart, which we refer to as NGDQN, on a collection of classic control domains. Without employing target networks, NGDQN significantly outperforms DQN without target networks, and performs no worse than DQN with target networks, suggesting that NGDQN stabilizes training and can help reduce the need for additional hyperparameter tuning. We also find that NGDQN is less sensitive to hyperparameter optimization relative to DQN. Together these results suggest that natural-gradient techniques can improve value-function optimization in deep reinforcement learning.

The prospect of UK firms implanting their staff with microchips in order to improve security and efficiency has raised concerns among trade unions. Several legal and financial firms in the UK are reportedly in discussions with a company responsible for fitting thousands of people with chips in Scandinavia. The chips, which are about the size of a grain of rice, are usually implanted beneath the skin between the thumb and forefinger and use radio-frequency identification (RFID) technology to allow people to replace physical key cards, IDs and even train tickets. Uber has halted testing of driverless vehicles after a woman was killed by one of their cars in Tempe, Arizona. The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph The giant human-like robot bears a striking resemblance to the military robots starring in the movie'Avatar' and is claimed as a world first by its creators from a South Korean robotic company Waseda University's saxophonist robot WAS-5, developed by professor Atsuo Takanishi and Kaptain Rock playing one string light saber guitar perform jam session A man looks at an exhibit entitled'Mimus' a giant industrial robot which has been reprogrammed to interact with humans during a photocall at the new Design Museum in South Kensington, London Electrification Guru Dr. Wolfgang Ziebart talks about the electric Jaguar I-PACE concept SUV before it was unveiled before the Los Angeles Auto Show in Los Angeles, California, U.S The Jaguar I-PACE Concept car is the start of a new era for Jaguar.

It's a dream long held by science-fiction writers: that one day we will be able to erase painful memories and create happy ones. But now scientists at Oxford University say that fiction is closer to reality than we might have thought. For they are on the cusp of developing technology that will enable us to rub out difficult episodes from the past, and make the best ones even better. By electronically tinkering with brain waves that cement our memories in place, we may soon be able to treat conditions including amnesia and post-traumatic stress disorder by removing what causes us distress altogether, said researcher Laurie Pycroft. Using the same techniques we will be able to insert what are being described as'memory prostheses' to enhance our recollections or even create new ones. The idea was the basis for the 1990 film Total Recall, based on a short story by Philip K Dick, in which Arnold Schwarzenegger's character Douglas Quaid takes a virtual vacation – only to discover the life he thought he was leading was a lie.

Picture the scenario: a'robo-doc' Artificial Intelligence program has examined your scans, read your medical records, taken into account your habits, your genes, and crunched through global population data and the latest medical research. All this has allowed it to correctly identify an early-stage cancer long before it could ever become a true threat. All that's left is for your GP to deliver the news with skilled compassion. The doctor has ample time now, liberated by legions of automated systems that cut through a once-impossible workload. The hospital, should you ever need to attend, is now a model of efficiency with cleaners, nurses and doctors all guided by apps to wherever care is needed next.

This issue is multifaceted as legal experts try to apply existing law to fast-evolving circumstances -- something that does not always work. There are also differences in national legal systems, so technology companies need to take a global perspective to ensure full realisation of all implications. Another way to protect intellectual property is through patents -- and here the law is even clearer. Patent law requires inventors to be individuals who contributed to the conception or conversion of a concept to a practicality. For example, if an AI created an entirely new semiconductor chip, it could not be protected by patents unless some human intervention took place in the creative process, such as through the person who programmed the AI.

In systems of multiple agents, identifying the cause of observed agent dynamics is challenging. Often, these agents operate in diverse, non-stationary environments, where models rely on hand-crafted environment-specific features to infer influential regions in the system's surroundings. To overcome the limitations of these inflexible models, we present GP-LAPLACE, a technique for locating sources and sinks from trajectories in time-varying fields. Using Gaussian processes, we jointly infer a spatio-temporal vector field, as well as canonical vector calculus operations on that field. Notably, we do this from only agent trajectories without requiring knowledge of the environment, and also obtain a metric for denoting the significance of inferred causal features in the environment by exploiting our probabilistic method. To evaluate our approach, we apply it to both synthetic and real-world GPS data, demonstrating the applicability of our technique in the presence of multiple agents, as well as its superiority over existing methods.

Learning from positive and unlabeled data or PU learning is the setting where a learner only has access to positive examples and unlabeled data. The assumption is that the unlabeled data can contain both positive and negative examples. This setting has attracted increasing interest within the machine learning literature as this type of data naturally arises in applications such as medical diagnosis and knowledge base completion. This article provides a survey of the current state of the art in PU learning. It proposes seven key research questions that commonly arise in this field and provides a broad overview of how the field has tried to address them.