What makes a paper independently reproducible? Debates on reproducibility center around intuition or assumptions but lack empirical results. Our field focuses on releasing code, which is important, but is not sufficient for determining reproducibility. We take the first step toward a quantifiable answer by manually attempting to implement 255 papers published from 1984 until 2017, recording features of each paper, and performing statistical analysis of the results. For each paper, we did not look at the authors code, if released, in order to prevent bias toward discrepancies between code and paper.

We investigate conjunctive normal form (CNF) encodings of a function represented with a smooth decomposable negation normal form (DNNF). Several encodings of DNNFs and decision diagrams were considered by (Abio et al. 2016). The authors differentiate between encodings which implement consistency or domain consistency from encodings which implement unit refutation completeness or propagation completeness (in both cases implements means by unit propagation). The difference is that in the former case we do not care about properties of the encoding with respect to the auxiliary variables while in the latter case we treat all variables (the input ones and the auxiliary ones) in the same way. The latter case is useful if a DNNF is a part of a problem containing also other constraints and a SAT solver is used to test satisfiability. The currently known encodings of smooth DNNF theories implement domain consistency. Building on this and the result of (Abio et al. 2016) on an encoding of decision diagrams which implements propagation completeness, we present a new encoding of a smooth DNNF which implements propagation completeness. This closes the gap left open in the literature on encodings of DNNFs.

Robots and self-driving vehicles face a number of challenges when navigating through real environments. Successful navigation in dynamic environments requires prioritizing subtasks and monitoring resources. Animals are under similar constraints. It has been shown that the neuromodulator serotonin regulates impulsiveness and patience in animals. In the present paper, we take inspiration from the serotonergic system and apply it to the task of robot navigation. In a set of outdoor experiments, we show how changing the level of patience can affect the amount of time the robot will spend searching for a desired location. To navigate GPS compromised environments, we introduce a deep reinforcement learning paradigm in which the robot learns to follow sidewalks. This may further regulate a tradeoff between a smooth long route and a rough shorter route. Using patience as a parameter may be beneficial for autonomous systems under time pressure.

RoboCup@Home is an international robotics competition based on domestic tasks requiring autonomous capabilities pertaining to a large variety of AI technologies. Research challenges are motivated by these tasks both at the level of individual technologies and the integration of subsystems into a fully functional, robustly autonomous system. We describe the progress made by the UT Austin Villa 2019 RoboCup@Home team which represents a significant step forward in AI-based HRI due to the breadth of tasks accomplished within a unified system. Presented are the competition tasks, component technologies they rely on, our initial approaches both to the components and their integration, and directions for future research.

Kettip Kriangchaivech 1 and Artit Wangperawong 2 1 kettipk@gmail.com 2 artit.wangperawong@usbank.com U.S. Bank 1095 Avenue of the Americas New Y ork, NY 10036 Abstract A machine learning model was developed to automatically generate questions from Wikipedia passages using transformers, an attention-based model eschewing the paradigm of existing recurrent neural networks (RNNs). The model was trained on the inverted Stanford Question Answering Dataset (SQuAD), which is a reading comprehension dataset consisting of 100,000 questions posed by crowdworkers on a set of Wikipedia articles. After training, the question generation model is able to generate simple questions relevant to unseen passages and answers containing an average of 8 words per question. The word error rate (WER) was used as a metric to compare the similarity between SQuAD questions and the model-generated questions. Although the high average WER suggests that the questions generated differ from the original SQuAD questions, the questions generated are mostly grammatically correct and plausible in their own right. Introduction Existing question generating systems reported in the literature involve human-generated templates, including cloze type (Hermann et al. 2015), rule-based (Mitkov and Ha 2003; Rus et al. 2010), or semiautomatic questions ( Alvaro and Alvaro 2010; Rey et al. 2012; Liu and Lin 2014). On the other hand, machine learned models developed recently have used recurrent neural networks (RNNs) to perform sequence transduction, i.e. sequence-to-sequence (Du, Shao, and Cardie 2017; Kim et al. 2019). In this work, we investigated an automatic question generation system based on a machine learning model that uses transformers instead of RNNs (V aswani et al. 2017; Wangperawong 2018).

As artificial intelligence and machine learning algorithms make further inroads into society, calls are increasing from multiple stakeholders for these algorithms to explain their outputs. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, present different requirements for explanations. Toward addressing these needs, we introduce AI Explainability 360 (http://aix360.mybluemix.net/), an open-source software toolkit featuring eight diverse and state-of-the-art explainability methods and two evaluation metrics. Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability. For data scientists and other users of the toolkit, we have implemented an extensible software architecture that organizes methods according to their place in the AI modeling pipeline. We also discuss enhancements to bring research innovations closer to consumers of explanations, ranging from simplified, more accessible versions of algorithms, to tutorials and an interactive web demo to introduce AI explainability to different audiences and application domains. Together, our toolkit and taxonomy can help identify gaps where more explainability methods are needed and provide a platform to incorporate them as they are developed.

Book a suite in a luxury hotel in Moscow, send the room number encrypted to a pre-determined mobile number and then wait for a return message indicating a precise time: Meeting Edward Snwoden is pretty much exactly how children imagine the grand game of espionage is played. But then, on Monday, there he was, standing in our room on the first floor of the Hotel Metropol, as pale and boyish-looking as the was when the world first saw him in June 2013. For the last six years, he has been living in Russian exile. The U.S. has considered him to be an enemy of the state, right up there with Julian Assange, ever since he revealed, with the help of journalists, the full scope of the surveillance system operated by the National Security Agency (NSA). For quite some time, though, he remained silent about how he smuggled the secrets out of the country and what his personal motivations were. Now, though, he has written a book about it. It will be published worldwide on September 17 under the title "Permanent Record." Ahead of publication, Snowden spent over two-and-a-half hours patiently responding to questions from DER SPIEGEL. DER SPIEGEL: Mr. Snowden, you always said: "I am not the story."

Shopify today announced it is acquiring 6 River Systems, a startup focused on fulfillment automation for ecommerce and retail operations. The deal is valued at approximately $450 million -- 60% in cash and 40% in shares. At its Unite partner and developer conference in June, the company announced its Shopify Fulfillment Network, which uses machine learning to ensure timely deliveries and lower shipping costs. Shopify's fulfillment centers span California, Georgia, New Jersey, Nevada, Ohio, Pennsylvania, and Texas. The network, which is only available in early access, supports merchants that ship between 10 and 10,000 packages per day.

Fri 13 Sep 2019 17.00 BST Last modified on Fri 13 Sep 2019 17.00 BST The world's most famous whistleblower, Edward Snowden, says he has detected a softening in public hostility towards him in the US over his disclosure of top-secret documents that revealed the extent of the global surveillance programmes run by American and British spy agencies. In an exclusive two-hour interview in Moscow to mark the publication of his memoirs, Permanent Record, Snowden said dire warnings that his disclosures would cause harm had not come to pass, and even former critics now conceded "we live in a better, freer and safer world" because of his revelations. In the book, Snowden describes in detail for the first time his background, and what led him to leak details of the secret programmes being run by the US National Security Agency (NSA) and the UK's secret communication headquarters, GCHQ. He describes the 18 years since the September 11 attacks as "a litany of American destruction by way of American self-destruction, with the promulgation of secret policies, secret laws, secret courts and secret wars". Snowden also said: "The greatest danger still lies ahead, with the refinement of artificial intelligence capabilities, such as facial and pattern recognition. "An AI-equipped surveillance camera would be not a mere recording device, but could be made into something closer to an automated police officer." He is concerned the US and other governments, aided by the big internet companies, are moving towards creating a permanent record of everyone on earth, recording the whole of their daily lives. While Snowden feels justified in what he did six years ago, he told the Guardian he was reconciled to being in Russia for years to come and was planning for his future on that basis. He reveals he secretly married his partner, Lindsay Mills, two years ago in a Russian courthouse. While he would rather be in the US or somewhere like Germany, he is relaxed in Russia, now able to lead a more or less normal daily life. He is less fearful than when he first arrived in 2013, when he felt lonely, isolated and paranoid that he could be targeted in the streets by US agents seeking retribution. "I was very much a person the most powerful government in the world wanted to go away.

This week on Microsoft Unboxed, our hosts Sonia and Colleen share stories of how companies are using AI in infrastructure – from roads to the bridges we drive on. First, Colleen shares a story from Denmark where AI-enabled drones are monitoring the Great Belt Bridge. Colleen explains why bridges need to be monitored due to the wear and tear over time to prevent cracks forming that may make them unsafe for driving. The monitoring has traditionally been done manually – but this is where AI comes in. Holding company Sund and Bælt partnered with Microsoft to implement a new technique that uses drones and thousands of images of the bridge to be analyzed by AI technology for cracks and safety issues.