Singapore has set up a council to advise its government on developing and using artificial intelligence. "The advisory council will assist the Government to develop ethics standards and reference governance frameworks, issue advisory guidelines, practical guidance and codes of practice for voluntary adoption by businesses," said Minister for Communications and Information S. Iswaran at the opening ceremony of the Innovfest Unbound conference yesterday. The council, being set up by the Infocomm Media Development Authority (IMDA), will work with the ethics boards of businesses. It also seeks to educate the private capital community to include ethics considerations in their AI-related investment decisions. The council will consist of AI users, representatives from technology companies, and others who will provide social and consumer perspectives.

Google is set to publish ethical guidelines for its use of artificial intelligence this week, after its decision not to renew a drone contract with the U.S. Department of Defense. According to Financial Times, the internet search company is widely regarded as having the most advanced AI. In fact, the Pentagon has been using Google's vision technology to help drones interpret objects on the ground. That relationship with the government resulted in fierce opposition inside the company, but it's not the only criticism Google has received regarding its use of AI. For example, the company's image search feature has come under fire for perpetuating preconceptions based on the data in Google's search index, such as a search for "CEOs" returning mostly white faces.

The world could fall behind China when it comes to developing artificial intelligence (AI), the former president of the European Commission warned Monday. Jose Manuel Barroso, now non-executive chairman at Goldman Sachs International, told CNBC's Arjun Kharpal that Beijing is getting on with development in AI. "The Chinese are not only making statements, they are investing money," he said at the AI Deep Dive in partnership with Feedzai at Money2020. Barroso added that his sentiment was not negative toward China and that, in the main, Chinese-led science would benefit the world. The Goldman employee said Europe, in particular, "should not be naive" and must defend itself by ensuring that more money is committed to AI development. He said there was evidence that this was happening with European countries that are net contributors to Brussels being asked to provide 100 billion euros ($117 billion) over the next seven years to scientific research.

The U.S. Department of Homeland Security (DHS) on Wednesday urged Congress to approve legislation giving the federal government new powers to disable or destroy threatening drones, according to testimony viewed by Reuters. David Glawe, DHS's undersecretary for intelligence and analysis, and the department's deputy general counsel Hayley Chang, will tell the Senate committee that oversees the department that it needs new authority. 'Terrorist groups overseas use drones to conduct attacks on the battlefield and continue to plot to use them in terrorist attacks elsewhere,' the officials' testimony said. Officials said the number of drone flights over sensitive areas or suspicious activities has jumped from eight incidents in 2013 to an estimated 1,752 incidents in 2016, citing federal statistics. 'This is a very serious, looming threat that we are currently unprepared to confront.

This document contains the outcome of the first Human behaviour and machine intelligence (HUMAINT) workshop that took place 5-6 March 2018 in Barcelona, Spain. The workshop was organized in the context of a new research programme at the Centre for Advanced Studies, Joint Research Centre of the European Commission, which focuses on studying the potential impact of artificial intelligence on human behaviour. The workshop gathered an interdisciplinary group of experts to establish the state of the art research in the field and a list of future research challenges to be addressed on the topic of human and machine intelligence, algorithm's potential impact on human cognitive capabilities and decision making, and evaluation and regulation needs. The document is made of short position statements and identification of challenges provided by each expert, and incorporates the result of the discussions carried out during the workshop. In the conclusion section, we provide a list of emerging research topics and strategies to be addressed in the near future.

We revisit the importance of the individual units in Convolutional Neural Networks (CNNs) for visual recognition. By conducting unit ablation experiments on CNNs trained on large scale image datasets, we demonstrate that, though ablating any individual unit does not hurt overall classification accuracy, it does lead to significant damage on the accuracy of specific classes. This result shows that an individual unit is specialized to encode information relevant to a subset of classes. We compute the correlation between the accuracy drop under unit ablation and various attributes of an individual unit such as class selectivity and weight L1 norm. We confirm that unit attributes such as class selectivity are a poor predictor for impact on overall accuracy as found previously in recent work \cite{morcos2018importance}. However, our results show that class selectivity along with other attributes are good predictors of the importance of one unit to individual classes. We evaluate the impact of random rotation, batch normalization, and dropout to the importance of units to specific classes. Our results show that units with high selectivity play an important role in network classification power at the individual class level. Understanding and interpreting the behavior of these units is necessary and meaningful.

During the past quarter-century, situation awareness (SAW) has become a critical research theme, because of its importance. Since the concept of SAW was first introduced during World War I, various versions of SAW have been researched and introduced. Predictive Situation Awareness (PSAW) focuses on the ability to predict aspects of a temporally evolving situation over time. PSAW requires a formal representation and a reasoning method using such a representation. A Multi-Entity Bayesian Network (MEBN) is a knowledge representation formalism combining Bayesian Networks (BN) with First-Order Logic (FOL). MEBN can be used to represent uncertain situations (supported by BN) as well as complex situations (supported by FOL). Also, efficient reasoning algorithms for MEBN have been developed. MEBN can be a formal representation to support PSAW and has been used for several PSAW systems. Although several MEBN applications for PSAW exist, very little work can be found in the literature that attempts to generalize a MEBN model to support PSAW. In this research, we define a reference model for MEBN in PSAW, called a PSAW-MEBN reference model. The PSAW-MEBN reference model enables us to easily develop a MEBN model for PSAW by supporting the design of a MEBN model for PSAW. In this research, we introduce two example use cases using the PSAW-MEBN reference model to develop MEBN models to support PSAW: a Smart Manufacturing System and a Maritime Domain Awareness System.

Recent work in fairness in machine learning has proposed adjusting for fairness by equalizing accuracy metrics across groups and has also studied how datasets affected by historical prejudices may lead to unfair decision policies. We connect these lines of work and study the residual unfairness that arises when a fairness-adjusted predictor is not actually fair on the target population due to systematic censoring of training data by existing biased policies. This scenario is particularly common in the same applications where fairness is a concern. We characterize theoretically the impact of such censoring on standard fairness metrics for binary classifiers and provide criteria for when residual unfairness may or may not appear. We prove that, under certain conditions, fairness-adjusted classifiers will in fact induce residual unfairness that perpetuates the same injustices, against the same groups, that biased the data to begin with, thus showing that even state-of-the-art fair machine learning can have a "bias in, bias out" property. When certain benchmark data is available, we show how sample reweighting can estimate and adjust fairness metrics while accounting for censoring. We use this to study the case of Stop, Question, and Frisk (SQF) and demonstrate that attempting to adjust for fairness perpetuates the same injustices that the policy is infamous for.

Multi-Entity Bayesian Network (MEBN) is a knowledge representation formalism combining Bayesian Networks (BN) with First-Order Logic (FOL). MEBN has sufficient expressive power for general-purpose knowledge representation and reasoning. Developing a MEBN model to support a given application is a challenge, requiring definition of entities, relationships, random variables, conditional dependence relationships, and probability distributions. When available, data can be invaluable both to improve performance and to streamline development. By far the most common format for available data is the relational database (RDB). Relational databases describe and organize data according to the Relational Model (RM). Developing a MEBN model from data stored in an RDB therefore requires mapping between the two formalisms. This paper presents MEBN-RM, a set of mapping rules between key elements of MEBN and RM. We identify links between the two languages (RM and MEBN) and define four levels of mapping from elements of RM to elements of MEBN. These definitions are implemented in the MEBN-RM algorithm, which converts a relational schema in RM to a partial MEBN model. Through this research, the software has been released as a MEBN-RM open-source software tool. The method is illustrated through two example use cases using MEBN-RM to develop MEBN models: a Critical Infrastructure Defense System and a Smart Manufacturing System.

For all of the recent focus on the cybersecurity talent shortages in the federal government, Suzette Kent said Wednesday that agencies will soon be battling for another in-demand skill set to help fuel its technology transformation: data science. While the workforce transformation and IT modernization goals of the President's Management Agenda are essential, they are undergirded by agencies' ability to analyze troves of government data, the federal CIO said at the Data Coalition's Data Demo Day. "Right now, we're just starting to see data science and analytics jobs pop up across the government," Kent said. "But we have to evolve roles for data scientists in deep learning development [and] inquiry designers. As we move down this path that is wholly data-driven, we need different types of capabilities in our workforce."