In 1901, on an excavation trip to Crete, British archaeologist Arthur Evans unearthed items he believed belonged to a royal game dating back millennia: a board fashioned out of ivory, gold, silver, and rock crystals, and four conical pieces nearby, assumed to be the tokens. Playing it, however, stumped Evans, and many others after him who took a stab at it. There was no rulebook, no hints, and no other copies have ever been found. Games need instructions for players to follow. Without any, the Greek board's function remained unresolved--that is, until recently. Enter artificial intelligence, and a group of researchers from Maastricht University in the Netherlands.

Researchers have mapped the web of connections underpinning coronavirus conspiracy theories, opening a new way of understanding and challenging them. Using Danish witchcraft folklore as a model, the researchers from UCLA and Berkeley analysed thousands of social media posts with an artificial intelligence tool and extracted the key people, things and relationships. The tool enabled them to piece together the underlying stories in coronavirus conspiracy theories from fragments in online posts. One discovery from the research identifies Bill Gates as the reason why conspiracy theorists connect 5G with the virus. With Gates' background in computer technology and vaccination programmes, he served as a shortcut for these storytellers to link the two.

We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network. The layers of a network are first expressed as factorized tensor layers. Tensor dropout is then applied in the latent subspace, therefore resulting in dense reconstructed weights, without the sparsity or perturbations typically induced by the randomization.Our approach can be readily integrated with any arbitrary neural architecture and combined with techniques like adversarial training. We empirically demonstrate the effectiveness of our approach on standard image classification benchmarks. We validate the versatility of our approach across domains and low-precision architectures by considering an audio classification task and binary networks. In all cases, we demonstrate improved performance compared to prior works.

Recent studies show that private training data can be leaked through the gradients sharing mechanism deployed in distributed machine learning systems, such as federated learning (FL). Increasing batch size to complicate data recovery is often viewed as a promising defense strategy against data leakage. In this paper, we revisit this defense premise and propose an advanced data leakage attack with theoretical justification to efficiently recover batch data from the shared aggregated gradients. We name our proposed method as catastrophic data leakage in vertical federated learning (CAFE). Comparing to existing data leakage attacks, our extensive experimental results on vertical FL settings demonstrate the effectiveness of CAFE to perform large-batch data leakage attack with improved data recovery quality. We also propose a practical countermeasure to mitigate CAFE. Our results suggest that private data participated in standard FL, especially the vertical case, have a high risk of being leaked from the training gradients. Our analysis implies unprecedented and practical data leakage risks in those learning settings. The code of our work is available at https://github.com/DeRafael/CAFE.

Expert system can process large amounts of known information and apply reasoning capabilities to provide conclusions. An expert system is a system that employs human knowledge captured in an automated system to solve problems that typically require human expertise. In this paper we propose the design and development of a medical knowledge based system (MKBS) for disease diagnosis from symptoms. It provides rich features for searching properties like symptoms, treatments, hierarchical clusters of particular diseases. The system supports a knowledge construction module and an inference engine module. The knowledge construction was built on a concept of rules, which was represented in a tree structure, and properties of a particular disease were stored as a semantic net.

We propose a three-stage framework for forecasting high-dimensional time-series data. Our method first estimates parameters for each univariate time series. Next, we use these parameters to cluster the time series. These clusters can be viewed as multivariate time series, for which we then compute parameters. The forecasted values of a single time series can depend on the history of other time series in the same cluster, accounting for intra-cluster similarity while minimizing potential noise in predictions by ignoring inter-cluster effects. Our framework -- which we refer to as "cluster-and-conquer" -- is highly general, allowing for any time-series forecasting and clustering method to be used in each step. It is computationally efficient and embarrassingly parallel. We motivate our framework with a theoretical analysis in an idealized mixed linear regression setting, where we provide guarantees on the quality of the estimates. We accompany these guarantees with experimental results that demonstrate the advantages of our framework: when instantiated with simple linear autoregressive models, we are able to achieve state-of-the-art results on several benchmark datasets, sometimes outperforming deep-learning-based approaches.

Recently, deep reinforcement learning (DRL) frameworks have shown potential for solving NP-hard routing problems such as the traveling salesman problem (TSP) without problem-specific expert knowledge. Although DRL can be used to solve complex problems, DRL frameworks still struggle to compete with state-of-the-art heuristics showing a substantial performance gap. This paper proposes a novel hierarchical problem-solving strategy, termed learning collaborative policies (LCP), which can effectively find the near-optimum solution using two iterative DRL policies: the seeder and reviser. The seeder generates as diversified candidate solutions as possible (seeds) while being dedicated to exploring over the full combinatorial action space (i.e., sequence of assignment action). To this end, we train the seeder's policy using a simple yet effective entropy regularization reward to encourage the seeder to find diverse solutions. On the other hand, the reviser modifies each candidate solution generated by the seeder; it partitions the full trajectory into sub-tours and simultaneously revises each sub-tour to minimize its traveling distance. Thus, the reviser is trained to improve the candidate solution's quality, focusing on the reduced solution space (which is beneficial for exploitation). Extensive experiments demonstrate that the proposed two-policies collaboration scheme improves over single-policy DRL framework on various NP-hard routing problems, including TSP, prize collecting TSP (PCTSP), and capacitated vehicle routing problem (CVRP).

Random projection (RP) have recently emerged as popular techniques in themachine learning community for their ability in reducing the dimension of veryhigh-dimensional tensors. Following the work in [29], we consider a tensorizedrandom projection relying on Tensor Train (TT) decomposition where each elementof the core tensors is drawn from a Rademacher distribution. Our theoreticalresults reveal that the Gaussian low-rank tensor represented in compressed formin TT format in [29] can be replaced by a TT tensor with core elements drawnfrom a Rademacher distribution with the same embedding size. Experiments onsynthetic data demonstrate that tensorized Rademacher RP can outperform thetensorized Gaussian RP studied in [29]. In addition, we show both theoreticallyand experimentally, that the tensorized RP in the Matrix Product Operator (MPO)format proposed in [5] for performing SVD on large matrices is not a Johnson-Lindenstrauss transform (JLT) and therefore not a well-suited random projectionmap

Bias correction techniques are used by most of the high-performing methods for off-policy reinforcement learning. However, these techniques rely on a pre-defined bias correction policy that is either not flexible enough or requires environment-specific tuning of hyperparameters. In this work, we present a simple data-driven approach for guiding bias correction. We demonstrate its effectiveness on the Truncated Quantile Critics -- a state-of-the-art continuous control algorithm. The proposed technique can adjust the bias correction across environments automatically. As a result, it eliminates the need for an extensive hyperparameter search, significantly reducing the actual number of interactions and computation.

Israel is holding its largest-ever air force exercise this week with the participation of several countries including the United Arab Emirates, with whom it normalised ties last year. Amir Lazar, chief of Israeli air force operations, told reporters at the southern Ovda airbase the drills "don't focus on Iran", but army officials have said Iran remains Israel's top strategic threat and at the centre of much of its military planning. Israel has held the so-called "Blue Flag" exercises every two years since 2013 in the Negev desert to synchronise different types of aircraft, piloted by different countries to counter armed drones and other threats. With more than 70 fighter jets and some 1,500 personnel participating, this year's drills are the largest-ever held in Israel, Lazar said. Among the nations taking part are France, the United States and Germany, as well as the United Kingdom, whose aircraft flew over Israeli territory for the first time since the Jewish state's creation in 1948.