Knowledge Graphs (KGs) have found many applications in industry and academic settings, which in turn, have motivated considerable research efforts towards large-scale information extraction from a variety of sources. Despite such efforts, it is well known that even state-of-the-art KGs suffer from incompleteness. Link Prediction (LP), the task of predicting missing facts among entities already a KG, is a promising and widely studied task aimed at addressing KG incompleteness. Among the recent LP techniques, those based on KG embeddings have achieved very promising performances in some benchmarks. Despite the fast growing literature in the subject, insufficient attention has been paid to the effect of the various design choices in those methods. Moreover, the standard practice in this area is to report accuracy by aggregating over a large number of test facts in which some entities are over-represented; this allows LP methods to exhibit good performance by just attending to structural properties that include such entities, while ignoring the remaining majority of the KG. This analysis provides a comprehensive comparison of embedding-based LP methods, extending the dimensions of analysis beyond what is commonly available in the literature. We experimentally compare effectiveness and efficiency of 16 state-of-the-art methods, consider a rule-based baseline, and report detailed analysis over the most popular benchmarks in the literature.

With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. This review summarises deep reinforcement learning (DRL) algorithms, provides a taxonomy of automated driving tasks where (D)RL methods have been employed, highlights the key challenges algorithmically as well as in terms of deployment of real world autonomous driving agents, the role of simulators in training agents, and finally methods to evaluate, test and robustifying existing solutions in RL and imitation learning.

We propose an algorithm to actively estimate the parameters of a linear dynamical system. Given complete control over the system's input, our algorithm adaptively chooses the inputs to accelerate estimation. We show a finite time bound quantifying the estimation rate our algorithm attains and prove matching upper and lower bounds which guarantee its asymptotic optimality, up to constants. In addition, we show that this optimal rate is unattainable when using Gaussian noise to excite the system, even with optimally tuned covariance, and analyze several examples where our algorithm provably improves over rates obtained by playing noise. Our analysis critically relies on a novel result quantifying the error in estimating the parameters of a dynamical system when arbitrary periodic inputs are being played. We conclude with numerical examples that illustrate the effectiveness of our algorithm in practice.

Data-driven approaches, most prominently deep learning, have become powerful tools for prediction in many domains. A natural question to ask is whether data-driven methods could also be used for numerical weather prediction. First studies show promise but the lack of a common dataset and evaluation metrics make inter-comparison between studies difficult. Here we present a benchmark dataset for data-driven medium-range weather forecasting, a topic of high scientific interest for atmospheric and computer scientists alike. We provide data derived from the ERA5 archive that has been processed to facilitate the use in machine learning models. We propose a simple and clear evaluation metric which will enable a direct comparison between different methods. Further, we provide baseline scores from simple linear regression techniques, deep learning models as well as purely physical forecasting models. All data is publicly available and the companion code is reproducible with tutorials for getting started. We hope that this dataset will accelerate research in data-driven weather forecasting.

The Directorate of Science Technology and Innovations (DSTI) and the United Nations Development Program (UNDP) have signed a Memorandum of Understanding (MoU) to continue collaboration on applied artificial intelligence for governance, entrepreneurship, and social good. The MoU signed in Freetown last week provides a framework of cooperation and collaboration for both institutions to contribute to the successful implementation of the National Innovation and Digital Strategy (NIDS), especially in areas of common interest. In October 2019, the UNDP Country Lab also known as the Accelerator Lab for Sierra Leone was launched to examine and explore emerging untapped resources to speedup national SDG performance. The UNDP Accelerator Labs are a network of 60 labs serving 78 countries with the collective aim of finding new evidence-based approaches to problem-solving with the use of artificial intelligence, testing, mapping, and experimentation. "DSTI and UNDP have been engaging since Day 1. However, this particular agreement focuses on how we can continue to make significant inroads in the implementation of the National Innovation and Digital Strategy," said Dr. Moinina David Sengeh.

Phoronix is the leading technology website for Linux hardware reviews, open-source news, Linux benchmarks, open-source benchmarks, and computer hardware tests. Africa Animation, VFX & Video Games Industry Report 2020-2025 – AI, ML & Deep Learning are Being Leveraged to Drive Hyper-Personalisation for Video Games – ResearchAndMarkets.com AI still doesn't have the common sense to understand human language

On Wednesday, Microsoft Corp. announced AI for Health, a new $40 million, five-year program and part of the AI for Good initiative, that will leverage artificial intelligence (AI) technology to empower researchers and organizations addressing some of the world's toughest challenges in health. "Artificial intelligence has the potential to solve some of humanity's greatest challenges, like improving the health of communities around the world," said Brad Smith, president, Microsoft. "We know that putting this powerful technology into the hands of experts tackling this problem can accelerate new solutions and improve access for underserved populations. That's why we created AI for Health." In a new era of tech intensity, in which technology is reshaping every organization and becoming embedded in the fabric of every aspect of our lives, digital advances will continue to reshape our world in profound ways.

This paper introduces the Sylvester graphical lasso (SyGlasso) that captures multiway dependencies present in tensor-valued data. The model is based on the Sylvester equation that defines a generative model. The proposed model complements the tensor graphical lasso (Greenewald et al., 2019) that imposes a Kronecker sum model for the inverse covariance matrix by providing an alternative Kronecker sum model that is generative and interpretable. A nodewise regression approach is adopted for estimating the conditional independence relationships among variables. The statistical convergence of the method is established, and empirical studies are provided to demonstrate the recovery of meaningful conditional dependency graphs. We apply the SyGlasso to an electroencephalography (EEG) study to compare the brain connectivity of alcoholic and nonalcoholic subjects. We demonstrate that our model can simultaneously estimate both the brain connectivity and its temporal dependencies.

Granger causality is a fundamental technique for causal inference in time series data, commonly used in the social and biological sciences. Typical operationalizations of Granger causality make a strong assumption that every time point of the effect time series is influenced by a combination of other time series with a fixed time delay. The assumption of fixed time delay also exists in Transfer Entropy, which is considered to be a non-linear version of Granger causality. However, the assumption of the fixed time delay does not hold in many applications, such as collective behavior, financial markets, and many natural phenomena. To address this issue, we develop variable-lag Granger causality and Transfer Entropy, generalizations of both Granger causality and Transfer Entropy that relax the assumption of the fixed time delay and allows causes to influence effects with arbitrary time delays. In addition, we propose a method for inferring both variable-lag Granger causality and Transfer Entropy relations. We demonstrate our approach on an application for studying coordinated collective behavior and other real-world casual-inference datasets and show that our proposed approaches perform better than several existing methods in both simulated and real-world datasets. Our approach can be applied in any domain of time series analysis. The software of this work is available in the R package: VLTimeSeriesCausality.

In the space of a single year, South African agritech enterprise Aerobotics has won numerous awards and made strategic inroads into the massively competitive US agriculture industry. Propelled by world-leading technology, the South African success story is poised to mushroom into a truly global data and analytics software company serving the entire agriculture value chain. Aerobotics, which as little as a year ago was nominated as one of South Africa's most exciting startups, turns imagery into actionable data so that any issues on the farm, or elsewhere in the value chain, can be identified and resolved before they become problems. In essence, Aerobotics exposes what the naked eye cannot see in order to solve problems and make accurate projections, translating into improved yields and profitability. The company's CEO, James Paterson, says the business is ready to build on its highly successful launch in the US and strategically drop further roots and extend services in numerous regions around the world.