We design two learning algorithms that simultaneously promise differential privacy and equalized odds, a 'fairness' condition that corresponds to equalizing false positive and negative rates across protected groups. Our first algorithm is a simple private implementation of the post-processing approach of [Hardt et al. 2016]. This algorithm has the merit of being exceedingly simple, but must be able to use protected group membership explicitly at test time, which can be viewed as 'disparate treatment'. The second algorithm is a differentially private version of the algorithm of [Agarwal et al. 2018], an oracle-efficient algorithm that can be used to find the optimal fair classifier, given access to a subroutine that can solve the original (not necessarily fair) learning problem. This algorithm need not have access to protected group membership at test time. We identify new tradeoffs between fairness, accuracy, and privacy that emerge only when requiring all three properties, and show that these tradeoffs can be milder if group membership may be used at test time.

For being potentially destructive, in practice incomprehensible and for the most unintelligible, contemporary technology is setting high challenges on our society. New conception methods are urgently required. Reorganizing ideas and discussions presented in AI and related fields, this position paper aims to highlight the importance of normware--that is, computational artifacts specifying norms--with respect to these issues, and argues for its irreducibility with respect to software by making explicit its neglected ecological dimension in the decision-making cycle.

If your professional interests take you to the crossroads of financial services, regulation, compliance, and digital - especially data analytics and machine learning - which altogether is known as regtech, you are in the right place. You are part of statistically small and very geek-oriented professional community, but you know this, and though you might choose not to admit this to strangers at this year's festive parties for fear of causing great pain by boredom, you are in good company with this Contributor and my interviewee. I first met Jo Ann Barefoot when I was chairing the U.K. Financial Conduct Authority (FCA) Industry Sandbox Consultation, where she provided excellent guidance and insights. Jo Ann is one of the most dedicated and busiest advocates of the regtech space on the planet and is truly outstanding in both her knowledge and passion in this area. She dedicates her time to a number of global bodies and initiatives related to regtech: she is a Senior Fellow Emerita at the Harvard Kennedy School Center for Business & Government, a Senior Advisor to the Omidyar network, sits on the fintech advisory committee for FINRA, is an Executive Board Member of the International RegTech Association (IRTA), is a member of the Milken Institute U.S. FinTech Advisory Committee, and chairs the boards of the Center for Financial Services Innovation and FinRegLab.

Artificial intelligence (AI) offers a major opportunity for global businesses, as the technology could add up to $15.7 trillion to the global economy by 2030. However, many businesses still struggle to actually use AI throughout the business to drive value and ROI, according to a Wednesday report from PwC. Of the 1,000 US executives surveyed, 20% said their companies will deploy AI across their businesses in 2019. However, major concerns over new privacy threats (43%), new cyberthreats (41%), new legal liabilities and reputational risk (34%), the technology's complexity (33%), and an inability to meet demand for AI skills (31%) stand in the way of implementation. Companies must focus on the following six key areas to become AI leaders, according to the report. SEE: IT leader's guide to the future of artificial intelligence (Tech Pro Research) Businesses will feel pressure in 2019 to scale AI initiatives to improve decision-making and forward-looking intelligence for workers across every department and function, PwC predicted.

John Hooker Carnegie Mellon University Revised December 2018 Abstract While many see the prospect of autonomous machines as threatening, autonomy may be exactly what we want in a superintelligent machine. There is a sense of autonomy, deeply rooted in the ethical literature, in which an autonomous machine is necessarily an ethical one. Development of the theory underlying this idea not only reveals the advantages of autonomy, but it sheds light on a number of issues in the ethics of artificial intelligence. It helps us to understand what sort of obligations we owe to machines, and what obligations they owe to us. It clears up the issue of assigning responsibility to machines or their creators. More generally, a concept of autonomy that is adequate to both human and artificial intelligence can lead to a more adequate ethical theory for both. There is a good deal of trepidation at the prospect of autonomous machines. They may wreak havoc and even turn on their creators. We fear losing control of machines that have minds of their own, particularly if they are intelligent enough to outwit us. There is talk of a "singularity" in technological development, at which point machines will start designing themselves and create superintelligence (Vinge 1993, Bostrom 2014). Do we want such machines to be autonomous? There is a sense of autonomy, deeply rooted in the ethics literature, in which this may be exactly what we want. The attraction of an autonomous machine, in this sense, is that it is an ethical machine. The aim of this paper is to explain why this is so, and to show that the associated theory can shed light on a number of issues in the ethics of artificial intelligence (AI).

Lawyers representing South Korean plaintiffs in a World War II labor court case against Japan's Nippon Steel & Sumitomo Metal Corp. have set a Dec. 24 deadline for the firm to show willingness to discuss a court verdict on compensation. If the firm fails to respond, the lawyers, who spoke after being denied a meeting with company officials for a second time on Tuesday, said they would start procedures to seize its South Korean assets. Tuesday's incident stemmed from a ruling by South Korea's Supreme Court late in October that Nippon Steel must pay 100 million won ($90,500) to each of four South Koreans for forced labor during the war. The Japanese government has denounced the verdict, saying all wartime reparations were dealt with in a 1965 treaty that normalized ties between the two nations. At the time of the ruling, Nippon Steel called it "extremely regrettable," but added that it would review the decision carefully in considering further steps.

As we survey the fallout from the midterm elections, it would be easy to miss the longer-term threats to democracy that are waiting around the corner. Perhaps the most serious is political artificial intelligence in the form of automated "chatbots," which masquerade as humans and try to hijack the political process. Chatbots are software programs that are capable of conversing with human beings on social media using natural language. Increasingly, they take the form of machine learning systems that are not painstakingly "taught" vocabulary, grammar and syntax but rather "learn" to respond appropriately using probabilistic inference from large data sets, together with some human guidance. Some chatbots, like the award-winning Mitsuku, can hold passable levels of conversation.

TOKYO (Reuters) - Lawyers representing South Korean plaintiffs in a World War Two forced labor court case against Japan's Nippon Steel & Sumitomo Metal Corp. have set a Dec. 24 deadline for the firm to show willingness to discuss a court verdict on compensation.

Legal Artificial Intelligence has made the news' headlines often, recently. There are chat bots, e.g., that help you appeal against a parking ticket (www.donotpay.co.uk), or give you a first advice if you are considering a divorce (divorce bot). There is software that predicts the likely outcome of court cases. IBM offers legal AI services for eDiscovery and legal research with its Watson supercomputer: Ross, as the service is called, uses Natural Language Processing, and can also be used for cognitive computing, e.g., to review contracts (www.rossintelligence.com). Then there is RPA (Robotics Process Automation) who are creating software robots for law firms.

Artificial Intelligence – specifically machine learning and deep learning – was everywhere in 2018 and don't expect the hype to die down over the next 12 months. The hype will die eventually of course, and AI will become another consistent thread in the tapestry of our lives, just like the internet, electricity, and combustion did in days of yore. But for at least the next year, and probably longer, expect astonishing breakthroughs as well as continued excitement and hyperbole from commentators. This is because expectations of the changes to business and society which AI promises (or in some cases threatens) to bring about go beyond anything dreamed up during previous technological revolutions. AI points towards a future where machines not only do all of the physical work, as they have done since the industrial revolution but also the "thinking" work – planning, strategizing and making decisions.