Answer set programming (ASP) is a well-established knowledge representation formalism that grew from the observation that stable models [33] of a logic program can be used to encode search problems [59, 62, 49]. ASP is rapidly gaining adoption, with applications in domains such as decision support for the Space Shuttle [63], product configuration [75], phylogenetic inference [45, 11], knowledge management [37], e-Tourism [65], biology [32], robotics [5], and machine learning [41, 12]. The success of ASP can, to a large extend, be explained by two factors. The first factor is a rich, first-order language, ASP-Core2 [13], to express knowledge in, with an easy-to-understand modeling methodology known as generate-define-and-test. The second factor is the availability of a large number of reliable tools -- grounders [31, 46] and solvers [28, 3, 16] -- that allow to efficiently compute stable models of a given logic program. Throughout its history, ASP has always benefited from progress in other domains of combinatorial search. For instance, the addition of conflict-driven clause learning (CDCL) [60] to Boolean satisfiability (SAT) solvers is often recognized as one of the most important leaps forward in SAT solving; this technique was very quickly adopted in ASP.

With the increasing popularity of graph-based learning, graph neural networks (GNNs) emerge as the essential tool for gaining insights from graphs. However, unlike the conventional CNNs that have been extensively explored and exhaustively tested, people are still worrying about the GNNs' robustness under the critical settings, such as financial services. The main reason is that existing GNNs usually serve as a black-box in predicting and do not provide the uncertainty on the predictions. On the other side, the recent advancement of Bayesian deep learning on CNNs has demonstrated its success of quantifying and explaining such uncertainties to fortify CNN models. Motivated by these observations, we propose UAG, the first systematic solution to defend adversarial attacks on GNNs through identifying and exploiting hierarchical uncertainties in GNNs. UAG develops a Bayesian Uncertainty Technique (BUT) to explicitly capture uncertainties in GNNs and further employs an Uncertainty-aware Attention Technique (UAT) to defend adversarial attacks on GNNs. Intensive experiments show that our proposed defense approach outperforms the state-of-the-art solutions by a significant margin.

Quantum machine learning models have the potential to offer speedups and better predictive accuracy compared to their classical counterparts. However, these quantum algorithms, like their classical counterparts, have been shown to also be vulnerable to input perturbations, in particular for classification problems. These can arise either from noisy implementations or, as a worst-case type of noise, adversarial attacks. These attacks can undermine both the reliability and security of quantum classification algorithms. In order to develop defence mechanisms and to better understand the reliability of these algorithms, it is crucial to understand their robustness properties in presence of both natural noise sources and adversarial manipulation. From the observation that, unlike in the classical setting, measurements involved in quantum classification algorithms are naturally probabilistic, we uncover and formalize a fundamental link between binary quantum hypothesis testing (QHT) and provably robust quantum classification. Then from the optimality of QHT, we prove a robustness condition, which is tight under modest assumptions, and enables us to develop a protocol to certify robustness. Since this robustness condition is a guarantee against the worst-case noise scenarios, our result naturally extends to scenarios in which the noise source is known. Thus we also provide a framework to study the reliability of quantum classification protocols under more general settings.

Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary. However, in many real-world applications, this assumption is violated, and using existing algorithms may result in a performance lag. To proactively search for a good future policy, we present a policy gradient algorithm that maximizes a forecast of future performance. This forecast is obtained by fitting a curve to the counter-factual estimates of policy performance over time, without explicitly modeling the underlying non-stationarity. The resulting algorithm amounts to a non-uniform reweighting of past data, and we observe that minimizing performance over some of the data from past episodes can be beneficial when searching for a policy that maximizes future performance. We show that our algorithm, called Prognosticator, is more robust to non-stationarity than two online adaptation techniques, on three simulated problems motivated by real-world applications.

Legal scholars have postulated that there have been three eras of American law to-date, consisting in chronological order of the initial Age of Discovery, the Age of Faith, and then the Age of Anxiety. An open question that has received erudite attention in legal studies is what the next era, the fourth era, might consist of, and for which various proposals exist including examples such as the Age of Consent, the Age of Information, etc. There is no consensus in the literature as yet on what the fourth era is, and nor whether the fourth era has already begun or will instead emerge in the future. This paper examines the potential era-elucidating impacts amid the advent of autonomous Artificial Intelligence Legal Reasoning (AILR), entailing whether such AILR will be an element of a fourth era or a driver of a fourth, fifth, or perhaps the sixth era of American law. Also, a set of meta-characteristics about the means of identifying a legal era changeover are introduced, along with an innovative discussion of the role entailing legal formalism versus legal realism in the emergence of the American law eras.

We show how to assess a language model's knowledge of basic concepts of morality. We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality. Models predict widespread moral judgments about diverse text scenarios. This requires connecting physical and social world knowledge to value judgements, a capability that may enable us to steer chatbot outputs or eventually regularize open-ended reinforcement learning agents. With the ETHICS dataset, we find that current language models have a promising but incomplete understanding of basic ethical knowledge. Our work shows that progress can be made on machine ethics today, and it provides a steppingstone toward AI that is aligned with human values.

The E.U. supports the Iranian nuclear deal as the Trump administration announces new sanctions. Iran's Revolutionary Guard on Saturday threatened to avenge the killing of its top general, saying it would go after everyone responsible for the January U.S. drone strike in Iraq. The guard's website quoted Gen. Hossein Salami as saying, "Mr. Our revenge for martyrdom of our great general is obvious, serious and real." FILE: Chief of Iran's Revolutionary Guard Gen. Hossein Salami speaks at a pro-government rally, in Tehran, Iran.

Dublin start-up Ubotica has brought its AI technology into orbit aboard a next-gen ESA satellite. Dublin-based Ubotica Technologies has announced that its AI tech has gone into orbit aboard the Earth observation satellite PhiSat-1, which was launched along with 52 other satellites on a European Space Agency (ESA) Vega rocket yesterday (3 September). The satellite is part of a programme funded by ESA and supported by Enterprise Ireland, in which deep-learning technology for the in-orbit processing of Earth observation data is being deployed on a European satellite for the first time. Ubotica's CVAI technology, built on the Intel Movidius Myriad 2 vision processing unit, will allow the satellite to make its own decisions rather than relying on humans down on the planet's surface, resulting in faster, more efficient applications being deployed on the satellite. In this instance, Ubotica's AI tech is being tasked with automatic cloud detection on images captured by the satellite's advanced hyperspectral sensor.

President Donald Trump said Saturday he has approved a deal in principle in which Oracle and Walmart will partner with the viral video-sharing app TikTok in the U.S., allowing the popular app to avoid a shutdown. "I have given the deal my blessing -- if they get it done that's great, if they don't that's okay too," Trump told reporters on the White House South Lawn before departing for North Carolina. "I approved the deal in concept." The U.S. Department of Commerce announced it would delay the prohibition of U.S. transactions with TikTok until next Sunday. Shortly after Trump's comments, Oracle announced it was chosen as TikTok's secure cloud provider and will become a minority investor with a 12.5% stake.

Machine learning becomes engaging when we face various challenges and thus finding suitable datasets relevant to the use case is essential. Flexibility refers to the number of tasks that it supports. For example, Microsoft's COCO( Common Objects in Context) is used for object classification, detection, and segmentation. Add a bunch of captions for the same, and we can use it as a dataset for an image caption generator as well. Well, when we are just starting, we shall be working with some of the small and standard machine learning datasets like the CIFAR-10, MNIS, Iris, etc.